INDEX

Explanations

dates and numerical data found in reports and statistics

oai_token-act-pair · gemini-2.0-flash

in

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 MainAxisSize

-0.55

 onAnimation

-0.51

 للمعارف

-0.49

imp

-0.48

ilim

-0.47

ram

-0.47

DropColumn

-0.46

җ

-0.46

boten

-0.46

mpa

-0.45

POSITIVE LOGITS

 pageContext

0.69

 AssemblyCulture

0.66

Datuak

0.65

 purpoſe

0.60

 againſt

0.60

 fubject

0.60

 linkovi

0.59

 Pinocchio

0.55

 ſeveral

0.55

NSYLVANIA

0.55

Activations Density 1.753%

dates and numerical data found in reports and statistics

in

No Comments

No Known Activations