INDEX

Explanations

words related to politics, conflict, agreements, and law

oai_token-act-pair · gemini-2.0-flash

peace

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

 peace

-0.91

 Peace

-0.79

 PEACE

-0.73

dot

-0.73

peace

-0.72

Peace

-0.72

dot

-0.68

 mxArray

-0.68

ScopeManager

-0.68

aarrggbb

-0.66

POSITIVE LOGITS

msgTypes

0.48

Externé

0.46

ManagedBean

0.45

AMPLES

0.43

бливості

0.42

unhofer

0.42

ceptibility

0.42

unjang

0.41

 drink

0.41

vány

0.41

Activations Density 12.099%

words related to politics, conflict, agreements, and law

peace

No Comments

No Known Activations