INDEX

Explanations

proper nouns representing organizations, brands, or locations

oai_token-act-pair · gemini-2.0-flash

Website snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

vnd

-0.39

kund

-0.39

bek

-0.39

陷

-0.39

XMLSchema

-0.39

saga

-0.38

üb

-0.38

 resourceCulture

-0.37

рь

-0.37

ins

-0.36

POSITIVE LOGITS

toMatchSnapshot

0.71

niająca

0.67

windowFixed

0.66

WebVitals

0.66

 typelib

0.65

 ProtoMessage

0.64

pośred

0.62

IsMutable

0.61

enumii

0.59

 betweenstory

0.59

Activations Density 2.190%

proper nouns representing organizations, brands, or locations

Website snippets

No Comments

No Known Activations