INDEX

Explanations

proper nouns and names of people.

oai_token-act-pair · gemini-2.0-flash

News and random topics

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

OrEqual

-0.48

Hin

-0.47

TypeDef

-0.47

mstyle

-0.45

erdo

-0.43

"}";

-0.42

不及

-0.42

endregion

-0.42

teren

-0.41

POSITIVE LOGITS

 however

0.83

InitVars

0.80

contentLoaded

0.74

 Taktlose

0.74

 though

0.73

évaluateur

0.73

 кстати

0.71

styleType

0.70

 although

0.69

 BrowserModule

0.68

Activations Density 1.898%

proper nouns and names of people.

News and random topics

No Comments

No Known Activations