INDEX

Explanations

function/method declarations and keywords, as well as basic programming syntax like colons, parentheses, braces, greater than/less than symbols

oai_token-act-pair · gemini-2.0-flash

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 JADX

-0.52

DotNetBar

-0.50

rague

-0.49

 noqa

-0.47

ického

-0.47

 angekommen

-0.47

راح

-0.45

쁘

-0.45

 apto

-0.44

 dirilis

-0.44

POSITIVE LOGITS

expandindo

0.71

 للمعارف

0.68

脚注の使い方

0.63

GEBURTSDATUM

0.63

tvguidetime

0.62

 resourceCulture

0.62

 дописавши

0.61

 StringTokenizer

0.60

nonatomic

0.60

Geplaatst

0.60

Activations Density 0.792%

function/method declarations and keywords, as well as basic programming syntax like colons, parentheses, braces, greater than/less than symbols

code

No Comments

No Known Activations