INDEX

Explanations

references to sections within legal acts

oai_token-act-pair · gemini-2.0-flash

legal documents

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

+:+

-0.53

verifyException

-0.52

 kasarigan

-0.51

Tē

-0.50

 Mans

-0.50

Che

-0.50

 otomatig

-0.50

styleType

-0.50

коменду

-0.49

Mili

-0.49

POSITIVE LOGITS

enderror

0.74

 vuitton

0.63

ftagPool

0.61

 BoxFit

0.56

 Chwiliwch

0.56

 saati

0.56

>--}}

0.52

 '\\;'

0.52

 réessayer

0.49

Efq

0.49

Activations Density 0.713%

references to sections within legal acts

legal documents

No Comments

No Known Activations