INDEX

Explanations

negative sentiment, judgment and opinion

oai_token-act-pair · gemini-2.0-flash

Interesting, strange, amazing

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

yarnpkg

-0.63

ReusableCell

-0.59

 елның

-0.57

cshtml

-0.56

uarts

-0.54

polate

-0.54

uolo

-0.53

 الميل

-0.53

uberge

-0.52

 Référence

-0.52

POSITIVE LOGITS

 things

1.17

 interesting

1.05

 strange

1.04

 amazing

0.98

 weird

0.95

 exciting

0.94

strange

0.90

 wonderful

0.90

interesting

0.88

Things

0.87

Activations Density 1.735%

negative sentiment, judgment and opinion

Interesting, strange, amazing

No Comments

No Known Activations