INDEX

Explanations

words meaning a piece or part of something

oai_token-act-pair · gemini-2.0-flash

aspect

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

yntaxException

-0.58

 parishi

-0.54

 beseech

-0.53

 Wherefore

-0.53

 Laus

-0.53

 sociologists

-0.53

SPATH

-0.52

GEBURTSDATUM

-0.52

 ویکی‌آمباردا

-0.52

ifflin

-0.52

POSITIVE LOGITS

 transfieras

0.69

EndContext

0.62

AnimationsModule

0.53

of

0.52

izada

0.52

 mergeFrom

0.51

IsContent

0.50

 Rises

0.50

contentLoaded

0.49

 pulumi

0.49

Activations Density 1.776%

words meaning a piece or part of something

aspect

No Comments

No Known Activations

words meaning a piece or part of something

aspect

No Comments

No Known Activations