INDEX

Explanations

code syntax like braces, parentheses, and certain keywords

oai_token-act-pair · gemini-2.0-flash

parentheses

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ScopeManager

-0.94

DockStyle

-0.84

 فريبيس

-0.74

:✨

-0.74

 оригіналу

-0.74

PreferredItem

-0.73

 صوتيه

-0.72

 المعيارى

-0.70

 وتسجيلات

-0.70

帖最后由

-0.70

POSITIVE LOGITS

0.54

Located

0.46

 TAMBÉM

0.44

 Located

0.41

lolo

0.41

efte

0.40

等

0.40

Basically

0.40

='

0.39

слу

0.38

Activations Density 1.518%

code syntax like braces, parentheses, and certain keywords

parentheses

No Comments

No Known Activations