INDEX

Explanations

a mix of HTML and programming code fragments related to playing a game or giving medical treatment

oai_token-act-pair · gemini-2.0-flash

Multiple languages

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

 яке

-0.76

 которое

-0.72

 estimés

-0.66

 welches

-0.61

 które

-0.61

eseorang

-0.57

 Оно

-0.53

 publiés

-0.52

 tiers

-0.52

 Arian

-0.52

POSITIVE LOGITS

iastes

0.54

 GenerationType

0.54

setLayoutParams

0.54

fjspx

0.52

 Вікіпе

0.52

клопе

0.52

gure

0.46

اتور

0.46

 مرئيه

0.45

 кӀ

0.45

Activations Density 2.016%

a mix of HTML and programming code fragments related to playing a game or giving medical treatment

Multiple languages

No Comments

No Known Activations