INDEX

Explanations

police and law enforcement related terms

oai_token-act-pair · gemini-2.0-flash

police

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olisian

-0.59

 police

-0.57

 parseFrom

-0.55

 مرئيه

-0.54

 Police

-0.54

 Polres

-0.54

'])){

-0.54

police

-0.51

 Poliz

-0.51

 polisi

-0.50

POSITIVE LOGITS

 SIMBAD

0.57

 Alembic

0.54

abetes

0.52

 uſed

0.52

Географиясе

0.51

 Familienname

0.51

 tourmaline

0.49

########.

0.49

 échou

0.49

 jadx

0.48

Activations Density 6.116%

police and law enforcement related terms

police

No Comments

No Known Activations