INDEX

Explanations

words related to software and web development

oai_token-act-pair · gemini-2.0-flash

coding tokens

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

قایناقلار

-0.52

 européennes

-0.52

 actifs

-0.49

<bos>

-0.49

 actif

-0.46

ловек

-0.45

 européens

-0.44

 tomber

-0.44

 públicos

-0.43

kháu

-0.43

POSITIVE LOGITS

XmlAccessorType

0.72

TagMode

0.60

jsonwebtoken

0.57

niająca

0.56

DataAnnotations

0.56

 onAnimation

0.55

 CommonModule

0.55

ⓧ

0.54

UserScript

0.54

 metav

0.54

Activations Density 11.809%

words related to software and web development

coding tokens

No Comments

No Known Activations