INDEX

Explanations

words and phrases related to crime and legal proceedings.

oai_token-act-pair · gemini-2.0-flash

criminal activity and proceedings

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

TintMode

-0.74

 <=",

-0.65

bootstrapcdn

-0.65

ConstraintMaker

-0.62

出版年

-0.62

 Normdatei

-0.59

AddHtmlAttribute

-0.59

Hentet

-0.57

 &___

-0.57

pexpr

-0.57

POSITIVE LOGITS

ban

0.54

 úteis

0.53

solete

0.51

newArrayList

0.50

anyeol

0.50

Deals

0.49

idenza

0.48

BAN

0.47

REDIRECT

0.47

árbol

0.47

Activations Density 5.159%

words and phrases related to crime and legal proceedings.

criminal activity and proceedings

No Comments

No Known Activations