INDEX

Explanations

references to scientific publications

oai_token-act-pair · gemini-2.0-flash

academic publications

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

 Expressway

-0.52

 boite

-0.45

Patches

-0.44

 considérons

-0.44

 AssemblyCulture

-0.42

 ujednoznacz

-0.42

byr

-0.42

 الرحمن

-0.42

TableCell

-0.41

 dinam

-0.40

POSITIVE LOGITS

 oprot

0.75

ⓧ

0.68

JspWriter

0.67

PreInfinity

0.66

 NgModule

0.65

Tikang

0.65

حياته

0.63

iseite

0.63

 useStyles

0.62

uyler

0.62

Activations Density 0.222%

references to scientific publications

academic publications

No Comments

No Known Activations