INDEX

Explanations

phrases involving "up to" followed by quantities or units of measure

oai_token-act-pair · gemini-2.0-flash

to

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

bibfield

-0.59

 allá

-0.56

writeFieldEnd

-0.55

 jusqu

-0.50

ljiv

-0.49

bibinfo

-0.48

 Jusqu

-0.48

FTFY

-0.47

zessin

-0.47

مصادر

-0.47

POSITIVE LOGITS

yyj

0.62

kháu

0.57

 indisponible

0.54

MergeFrom

0.49

فعل

0.48

esModule

0.48

<?

0.48

Personensuche

0.47

 duran

0.47

ynb

0.47

Activations Density 6.047%

phrases involving "up to" followed by quantities or units of measure

to

No Comments

No Known Activations