INDEX

Explanations

closing delimiters in nested blocks of code written in a variety of programming languages

oai_token-act-pair · gemini-2.0-flash

Parenthesis, brackets

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

 superiori

-0.43

ammlung

-0.42

 représentants

-0.41

 commerciali

-0.40

Transkript

-0.40

 disambiguazione

-0.40

ากาศ

-0.39

 rubia

-0.39

 चीज़ों

-0.39

 burying

-0.38

POSITIVE LOGITS

Tikang

0.71

">—

0.66

ValueStyle

0.63

})$}

0.59

 مشين

0.59

parsedMessage

0.57

 незавершена

0.56

انيف

0.56

WriteAttribute

0.54

 onCreateView

0.54

Activations Density 1.351%

closing delimiters in nested blocks of code written in a variety of programming languages

Parenthesis, brackets

No Comments

No Known Activations