INDEX

Explanations

words related to the law or legal proceedings

oai_token-act-pair · gemini-2.0-flash

these

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 IEnumerator

-0.56

 genoux

-0.53

bukkit

-0.51

 punte

-0.51

PropertyChanging

-0.49

 JTextField

-0.49

 réfrig

-0.49

 convaincre

-0.48

 vägen

-0.48

 prédé

-0.47

POSITIVE LOGITS

 مشين

0.75

 autorytatywna

0.71

참고

0.63

 Osorio

0.61

 ground

0.60

JspWriter

0.59

fjspx

0.58

^(@)

0.56

 ISNI

0.54

sup

0.54

Activations Density 1.263%

words related to the law or legal proceedings

these

No Comments

No Known Activations