INDEX

Explanations

geographical directions and abbreviations

oai_token-act-pair · gemini-2.0-flash

compass directions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

key

-0.44

LETED

-0.43

Captor

-0.42

 lietu

-0.41

uc

-0.41

نظ

-0.41

 fram

-0.41

 pass

-0.41

 measure

-0.41

Page

-0.40

POSITIVE LOGITS

 AssemblyCompany

0.85

zzleHttp

0.80

󠁢

0.79

 للاسماء

0.77

 Audiodateien

0.76

 AssemblyCulture

0.75

sidemargin

0.73

cshtml

0.70

 centrale

0.68

 arşivlendi

0.68

Activations Density 0.660%

geographical directions and abbreviations

compass directions

No Comments

No Known Activations

geographical directions and abbreviations

compass directions

No Comments

No Known Activations