INDEX

Explanations

C code syntax

oai_token-act-pair · gemini-2.0-flash

code/technical info

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

InstrumentedTest

-0.89

webElementXpaths

-0.79

addCriterion

-0.72

WireFormatLite

-0.71

homonymie

-0.71

AsUp

-0.68

 estekak

-0.65

KEYCODE

-0.65

twimg

-0.61

QMetaType

-0.61

POSITIVE LOGITS

 major

0.52

major

0.41

key

0.41

moid

0.40

REV

0.39

ようになります

0.38

 hash

0.38

டி

0.38

hw

0.38

bricht

0.37

Activations Density 6.543%

C code syntax

code/technical info

No Comments

No Known Activations