INDEX

Explanations

code license headers and/or words in a Kannada language transliteration

oai_token-act-pair · gemini-2.0-flash

Code/Technical documentation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

脚注の使い方

-0.66

__":

-0.60

Bronnen

-0.56

@[+][

-0.53

 Jurí

-0.52

RSpec

-0.52

 jurídica

-0.51

 незавершена

-0.51

níky

-0.50

níka

-0.50

POSITIVE LOGITS

keyColumn

0.56

parsedMessage

0.53

encodeWith

0.52

unmodifiable

0.51

 ultimi

0.51

ItemLayout

0.50

ṇa

0.50

 fréquent

0.49

@"/

0.49

 Pers

0.48

Activations Density 0.438%

code license headers and/or words in a Kannada language transliteration

Code/Technical documentation

No Comments

No Known Activations