INDEX

Explanations

words related to legal proceedings

oai_token-act-pair · gemini-2.0-flash

legal context and crimes

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

 Мексичка

-0.67

GEBURTSDATUM

-0.52

 ComVisible

-0.49

MigrationBuilder

-0.48

 useAppContext

-0.46

 ویکی‌پدی

-0.46

 Chwiliwch

-0.44

Enllaces

-0.43

 désolés

-0.42

GenerationType

-0.41

POSITIVE LOGITS

 obstin

0.67

 prejudicial

0.63

Erstellt

0.63

 unlaw

0.63

criminate

0.62

 endangering

0.62

 inhum

0.60

 obnoxious

0.60

lethal

0.60

findpost

0.59

Activations Density 17.716%

words related to legal proceedings

legal context and crimes

No Comments

No Known Activations