INDEX

Explanations

mentions of danger or threats

oai_token-act-pair · gemini-2.0-flash

threat

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 HasFactory

-0.49

 Neop

-0.48

PropertyChanging

-0.48

☜

-0.47

KommentareTeilen

-0.47

OrWhiteSpace

-0.47

 endwhile

-0.47

BagLayout

-0.47

rtype

-0.46

 Trix

-0.46

POSITIVE LOGITS

saraba

0.68

 podjela

0.50

nezeu

0.49

patine

0.48

schild

0.48

inghouse

0.48

惮

0.48

 يتيمه

0.47

ombo

0.47

发表于

0.46

Activations Density 1.357%

mentions of danger or threats

threat

No Comments

No Known Activations