INDEX

Explanations

words related to maintaining or continuing existence

oai_token-act-pair · gemini-2.0-flash

preservation, survival

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

<bos>

-0.96

copg

-0.61

Chham

-0.60

 mergeFrom

-0.56

 linkovi

-0.53

 jäsen

-0.52

balleur

-0.52

 kasarigan

-0.52

tamment

-0.52

IsMutable

-0.52

POSITIVE LOGITS

Personensuche

0.70

0.58

 AssemblyProduct

0.57

ⓧ

0.56

awtextra

0.52

textwidth

0.52

inaire

0.52

utory

0.52

utilisons

0.51

 DBNull

0.51

Activations Density 1.585%

words related to maintaining or continuing existence

preservation, survival

No Known Activations