INDEX

Explanations

words related to investigation or research

oai_token-act-pair · gemini-2.0-flash

data and evidence reviews

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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



-0.86

kuuta

-0.71

enumii

-0.70

 cdti

-0.69

 snippetHide

-0.69

 photolibrary

-0.65

存于互联网档案馆

-0.65

aratus

-0.65

 bezeichneter

-0.65

发表于

-0.64

POSITIVE LOGITS

UseVisualStyle

0.43

Pautan

0.42

yip

0.41

рон

0.41

detectChanges

0.40

Билгалдахарш

0.40

 makes

0.40

TintMode

0.40

 dépôt

0.40

 sambung

0.39

Activations Density 4.559%

words related to investigation or research

data and evidence reviews

No Comments

No Known Activations