INDEX

Explanations

code snippets and math formulas

oai_token-act-pair · gemini-2.0-flash

(

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

 calendriers

-0.52

 vermelhas

-0.51

urig

-0.50

assigns

-0.50

UpInside

-0.48

 vectorielles

-0.48

jface

-0.48

 maïs

-0.47

šice

-0.47

 femininas

-0.47

POSITIVE LOGITS

 архивлан

0.66

ParallelGroup

0.60

Javadoc

0.59

::::::::

0.53

ANTLR

0.53

Newswire

0.52

حياته

0.52

 насељу

0.52

>>();

0.52

 secular

0.51

Activations Density 5.732%

code snippets and math formulas

(

No Comments

No Known Activations