INDEX

Explanations

a variety of formatting codes and labels, including headings, subheadings, and document preparation terms

oai_token-act-pair · gemini-2.0-flash

non-english

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

/>";

-0.56

^(@)

-0.52

 AssemblyCulture

-0.48

nhung

-0.47

DockStyle

-0.45

terday

-0.43

 FontWeight

-0.43

 onAnimation

-0.43

 />";

-0.42

ToRefresh

-0.42

POSITIVE LOGITS

 ویکی‌پدی

0.74

новниш

0.55

RepeatedField

0.53

cupa

0.51

Bibliograf

0.50

LPD

0.49

vatel

0.49

LookAnd

0.47

enterOuterAlt

0.47

ть

0.46

Activations Density 0.602%

a variety of formatting codes and labels, including headings, subheadings, and document preparation terms

non-english

No Comments

No Known Activations