INDEX

Explanations

words and phrases common in judgements

oai_token-act-pair · gemini-2.0-flash

legal context

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

 kasarigan

-0.59

}>;

-0.54

ReusableCell

-0.53

EndContext

-0.53

galan

-0.51

 Reprodu

-0.49

 وتسجيلات

-0.49

EXEC

-0.48

!("{}",

-0.47

 défend

-0.47

POSITIVE LOGITS

Personensuche

0.69

 betweenstory

0.61

ModelAdmin

0.57

0.56

väg

0.55

 considérons

0.53

 SwitchCompat

0.52

ArrowToggle

0.51

afin

0.50

 /\.(

0.49

Activations Density 3.674%

words and phrases common in judgements

legal context

No Comments

No Known Activations