INDEX

Explanations

negative sentiment or judgement

oai_token-act-pair · gemini-2.0-flash

bad

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

bad

-2.66

Bad

-2.28

bad

-2.28

Bad

-2.22

BAD

-1.90

BAD

-1.78

 schlechte

-1.14

 mauvaise

-1.06

 mauvais

-1.03

 slecht

-1.03

POSITIVE LOGITS

 AssemblyCulture

0.73

CppMethod

0.65

uggle

0.60

LookAnd

0.59

 wireType

0.56

 étrang

0.56

PreferredItem

0.53

 profondità

0.53

BeginContext

0.53

 Tackle

0.52

Activations Density 2.525%

negative sentiment or judgement

bad

No Comments

No Known Activations