INDEX

Explanations

words or short phrases that represent the topic of a document.

oai_token-act-pair · gemini-2.0-flash

storytelling

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

出版年

-0.71

ⓧ

-0.68

ConstraintMaker

-0.65

<![

-0.61

DOCTYPE

-0.56

KURZBESCHREIBUNG

-0.54

 forState

-0.54

setVerticalGroup

-0.54

XmlAccessType

-0.53

Ano

-0.52

POSITIVE LOGITS

تیاز

0.47

DropTable

0.46

UrlResolution

0.46

tidase

0.45

GetBytes

0.45

parsedMessage

0.44

AntiForgeryToken

0.44

DoubleQuotes

0.43

itigation

0.43

運び

0.42

Activations Density 2.104%

words or short phrases that represent the topic of a document.

storytelling

No Comments

No Known Activations