INDEX

Explanations

words related to crime

oai_token-act-pair · gemini-2.0-flash

News or technical text

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

 ProtoMessage

-0.59

+#+

-0.58

 Administrativna

-0.57

SharedDtor

-0.57

 validés

-0.53

sproz

-0.52

 rodríguez

-0.52

IPAC

-0.52

 Italijanski

-0.50

+#+#

-0.49

POSITIVE LOGITS

PMailer

0.52

astify

0.50

Datuak

0.50

География

0.48

脚注の使い方

0.46

lied

0.46

[]:

0.46

CodeAttribute

0.45

EndContext

0.45

aksana

0.45

Activations Density 14.204%

words related to crime

News or technical text

No Comments

No Known Activations