INDEX

Explanations

an abbreviation for "apartment," "apathy," or "appendix."

oai_token-act-pair · gemini-2.0-flash

Ap

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

LayoutStyle

-0.81

MigrationBuilder

-0.76

archiviato

-0.65

RegistryLite

-0.64

ap

-0.63

reportWebVitals

-0.62

ngOn

-0.60

serviceWorker

-0.59

findpost

-0.59

 initComponents

-0.59

POSITIVE LOGITS

UserScript

0.42

Bix

0.41

InjectAttribute

0.41

KEYCODE

0.40

skrä

0.39

wing

0.38

 WING

0.38

 cobran

0.38

WING

0.38

int

0.37

Activations Density 1.415%

an abbreviation for "apartment," "apathy," or "appendix."

Ap

No Comments

No Known Activations