Embeddings are ubiquitous in machine learning, appearing in recommender systems, NLP, and many other applications. it’s natural to view tensors(or slices of tensors) as points in space, so almost any TF system will naturally give rise to various embeddings.

TensorBoard has a built-in visualizer, called the Embedding Projector, for interactive visualization and analysis of high-dimensional data like embeddings.

by default, the Embedding Projector projects the high_dimensional data into 3D using PCA. anothre useful projection you can use is t-SNE.