INDEX

Explanations

figure file names and related terms, especially from research papers

oai_token-act-pair · gemini-2.0-flash

code snippets/documentation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ngths

-0.54

taste

-0.47

…’

-0.46

 balan

-0.44

’?

-0.44

 aback

-0.43

hae

-0.43

 taste

-0.43

 censiti

-0.42

 betweenstory

-0.42

POSITIVE LOGITS

__(/*!

0.66

 vectorielle

0.59

 &___

0.59

 feroit

0.59

moveToFirst

0.58

 magnétique

0.58

listdir

0.57

Архівовано

0.57

 vectorielles

0.57

/*

0.57

Activations Density 16.460%

figure file names and related terms, especially from research papers

code snippets/documentation

No Comments

No Known Activations