INDEX

Explanations

words related to statistical or factual reporting and academic research

oai_token-act-pair · gemini-2.0-flash

exception to the norm

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للاسماء

-0.63

Życiorys

-0.59

 createState

-0.55

addGap

-0.47

ptonshire

-0.47

\{\\

-0.46

devamını

-0.45

영어

-0.45

gameserver

-0.44

 AssemblyProduct

-0.44

POSITIVE LOGITS

خواندن

0.59

цездатний

0.54

 AspNetCore

0.54

 canina

0.54

aarrggbb

0.54

openConnection

0.53

क्या

0.53

 Réponses

0.51

 jacques

0.51

 tört

0.50

Activations Density 56.337%

words related to statistical or factual reporting and academic research

exception to the norm

No Comments

No Known Activations