INDEX

Explanations

LaTeX math mode expressions, especially those with specific formatting commands

oai_token-act-pair · gemini-2.0-flash

${\

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

 стаття

-0.50

 समीक्षाएं

-0.47

yyr

-0.47

Personensuche

-0.45

TextWatcher

-0.44

RUnlock

-0.43

اخته

-0.43

terase

-0.41

 تكبرها

-0.41

הערות

-0.41

POSITIVE LOGITS

/******/

0.68

providedIn

0.62

#+#

0.61

tvguidetime

0.58

Portály

0.58

steamcommunity

0.56

otis

0.55

 étanche

0.54

ubin

0.54

opensource

0.54

Activations Density 4.516%

LaTeX math mode expressions, especially those with specific formatting commands

${\

No Comments

No Known Activations