INDEX

Explanations

instructions for navigating a user interface

oai_token-act-pair · gemini-2.0-flash

right

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 nahilalakip

-0.54

 leña

-0.52

 giù

-0.50

LinkId

-0.50

RenderAtEndOf

-0.47

orElseThrow

-0.45

 essais

-0.44

posób

-0.44

Facades

-0.43

 Федера

-0.42

POSITIVE LOGITS

ponses

0.59

Glej

0.58

Izvori

0.56

참고

0.55

ptid

0.54

Sklici

0.53

 Sack

0.53

:+:

0.52

 SafeMath

0.52

Kjelder

0.52

Activations Density 0.355%

instructions for navigating a user interface

right

No Comments

No Known Activations