INDEX

Explanations

uppercase character followed by "M"

oai_token-act-pair · 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

aarrggbb

-0.81

oredCriteria

-0.75

Vidite

-0.73

 SIMBAD

-0.72

 defaultstate

-0.70

 useAppContext

-0.69

حوالہ

-0.68

 itſelf

-0.66

iotensin

-0.66

Carriera

-0.66

POSITIVE LOGITS

ATCH

0.43

ouse

0.43

ass

0.42

arti

0.41

atch

0.40

at

0.40

WebServlet

0.40

ob

0.40

ano

0.38

os

0.38

Activations Density 4.239%

uppercase character followed by "M"

No Comments

No Known Activations