INDEX

Explanations

Dutch words and initialisms

oai_token-act-pair · gemini-2.0-flash

Code-related terms

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

LookAnd

-0.74

 consulté

-0.59

++]=

-0.52

ыгана

-0.50

getEnd

-0.50

ształ

-0.49

&_

-0.49

expandindo

-0.48

 vecchia

-0.48

bitField

-0.48

POSITIVE LOGITS

LEncoder

0.68

Xna

0.59

+#+

0.57

/**

0.55

asgi

0.54

Spoljašnje

0.52

 patron

0.51

 AssemblyTitle

0.51

classnames

0.51

#+#

0.50

Activations Density 0.314%

Dutch words and initialisms

Code-related terms

No Comments

No Known Activations