INDEX

Explanations

words related to people and places

oai_token-act-pair · gemini-2.0-flash

European people/history

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

fjspx

-0.68

kuuta

-0.66

日閲覧

-0.65

writeFieldEnd

-0.63

țiunea

-0.61

 disambiguazione

-0.61

ⓧ

-0.61

 saites

-0.60

 mouseY

-0.60

Erreferentziak

-0.59

POSITIVE LOGITS

Rob

0.47

expected

0.43

Il

0.41

Bett

0.41

Expecting

0.41

 battre

0.41

 chão

0.41

native

0.41

Ec

0.40

感

0.40

Activations Density 0.907%

words related to people and places

European people/history

No Comments

No Known Activations