INDEX

Explanations

mentions of news articles, publications, and writing

oai_token-act-pair · gemini-2.0-flash

news sources

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

endphp

-0.59

createCanvas

-0.55

</tfoot>

-0.48

vist

-0.43

Redraw

-0.42

GetField

-0.42

fill

-0.42

ANDER

-0.42

CGI

-0.42

BooleanField

-0.41

POSITIVE LOGITS

AddTagHelper

0.91

 للمعارف

0.87

 Buzz

0.70

MigrationBuilder

0.70

참고

0.69

@"/

0.68

tvguidetime

0.68

IsContent

0.67

 الرياضيه

0.67

ArrowToggle

0.64

Activations Density 3.947%

mentions of news articles, publications, and writing

news sources

No Comments

No Known Activations