INDEX

Explanations

content from scientific papers or textbooks

oai_token-act-pair · gemini-2.0-flash

research publications

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

protoimpl

-0.91

 "..\..\

-0.90

 "..\..\..\

-0.88

parsedMessage

-0.85

хьтан

-0.84

 pleaſure

-0.83

Tikang

-0.79

XmlAccessorType

-0.79

Personendaten

-0.78

WebVitals

-0.76

POSITIVE LOGITS

 within

0.59

up

0.54

 Within

0.50

within

0.47

 together

0.47

án

0.43

 générale

0.43

0.42

 Aplikasi

0.42

Activations Density 17.302%

content from scientific papers or textbooks

research publications

No Comments

No Known Activations