INDEX

Explanations

text related to law enforcement, prisons, or schools.

oai_token-act-pair · gemini-2.0-flash

Locations/rooms

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

AndEndTag

-0.72

webElement

-0.63

 Rooms

-0.60

IntoConstraints

-0.59

 iprot

-0.57

__*/

-0.57

 unknownFields

-0.55

ScopeManager

-0.55

vician

-0.54

ContentAlignment

-0.54

POSITIVE LOGITS

UserScript

0.56

 שוליים

0.50

lorette

0.50

通販

0.49

 NUKAT

0.48

edn

0.47

أس

0.47

 Spec

0.46

はじめに

0.46

Sitemap

0.46

Activations Density 3.335%

text related to law enforcement, prisons, or schools.

Locations/rooms

No Comments

No Known Activations