INDEX

Explanations

place names including cemeteries, churches and government

oai_token-act-pair · gemini-2.0-flash

Named locations

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

fores

-0.48

setDo

-0.45

ge

-0.45

 LUMI

-0.43

domain

-0.43

 stolen

-0.42

WAYS

-0.42

 geos

-0.41

dis

-0.41

 quanti

-0.41

POSITIVE LOGITS

 autorytatywna

0.78

tvguidetime

0.76

aarrggbb

0.69

 Normdatei

0.67

ագրություններ

0.66

featureID

0.65

StructEnd

0.63

исленность

0.63

IsMutable

0.58

StoryboardSegue

0.57

Activations Density 7.534%

place names including cemeteries, churches and government

Named locations

No Comments

No Known Activations