INDEX

Explanations

computer code

oai_token-act-pair · gemini-2.0-flash

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

يميديا

-0.69

-0.58

indd

-0.58

ंदीखरीदारी

-0.54

protoimpl

-0.54

sendStatus

-0.52

FetchType

-0.52

тистика

-0.51

#+#

-0.51

LookAnd

-0.51

POSITIVE LOGITS

 externi

0.60

 EconPapers

0.59

UnusedPrivate

0.59

uxxxx

0.59

StoryboardSegue

0.57

 препратки

0.55

+#+#

0.55

Geplaatst

0.54

TagMode

0.53

Jeografia

0.52

Activations Density 41.143%

computer code

code

No Comments

No Known Activations