INDEX

Explanations

words relating to nerves and/or sensation

oai_token-act-pair · gemini-2.0-flash

sensation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 betweenstory

-0.59

TAGS

-0.57

addContainerGap

-0.57

ItemLayout

-0.53

ukone

-0.52

Manbalar

-0.50

مراجع

-0.50

 TAGS

-0.49

tru

-0.49

UnknownFields

-0.49

POSITIVE LOGITS

Geografi

0.60

 ComVisible

0.55

tableFuture

0.53

ειτουργ

0.49

 referenties

0.48

__).

0.48

 responden

0.47

 tracci

0.47

GeneratedCode

0.45

 FLOOD

0.45

Activations Density 1.037%

words relating to nerves and/or sensation

sensation

No Comments

No Known Activations