INDEX

Explanations

business oriented language and statistics from texts related to medicine

oai_token-act-pair · gemini-2.0-flash

to

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ViewFeatures

-0.68

 deal

-0.65

 Italijanski

-0.63

 Deal

-0.62

 ErrIntOverflow

-0.61

getMenuInflater

-0.60

Deal

-0.59

 DEAL

-0.59

esModule

-0.58

eloma

-0.57

POSITIVE LOGITS

Gegen

0.43

 ويكيميديا

0.43

under

0.42

Blurb

0.42

 under

0.41

Artículo

0.41

Under

0.41

 <<<<<<<<<<<<<<

0.40

hydrates

0.39

 vnder

0.39

Activations Density 6.150%

business oriented language and statistics from texts related to medicine

to

No Comments

No Known Activations