INDEX

Explanations

words related to international relations, politics and terrorism

oai_token-act-pair · gemini-2.0-flash

foreign

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

setVerticalGroup

-0.85

 Италијани

-0.84

 propOrder

-0.84

 تضيفلها

-0.82

rrggbb

-0.79

ReusableCell

-0.77

TagMode

-0.75

 <>",

-0.73

InteropServices

-0.73

MessageTagHelper

-0.72

POSITIVE LOGITS

 angef

0.46

 legislatures

0.45

 tribune

0.44

 spies

0.44

 secretaries

0.43

Життєпис

0.41

 legislature

0.40

 ministers

0.39

 editors

0.39

âmara

0.39

Activations Density 8.393%

words related to international relations, politics and terrorism

foreign

No Comments

No Known Activations