INDEX

Explanations

words related to dates, locations or times

oai_token-act-pair · gemini-2.0-flash

Documentation and locations

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

 Polsek

-0.45

kyl

-0.45

 appartiennent

-0.45

MessageOf

-0.45

ObjectContext

-0.42

wydd

-0.42

 volontaire

-0.42

 européennes

-0.42

 Will

-0.41

 तब

-0.41

POSITIVE LOGITS

 ***!

0.83

 Paglinawan

0.73

__':

0.69

 ostavi

0.66

ParallelGroup

0.64

 referenties

0.64

__":

0.63

NameInMap

0.63

__':

0.63

EnableWeb

0.63

Activations Density 0.086%

words related to dates, locations or times

Documentation and locations

No Comments

No Known Activations