INDEX

Explanations

gibberish. It activates on parts of words in foreign languages, seemingly random collections of letters, and numbers. It also activates on "funds."

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 Normdatei

-0.83

 بلکه

-0.64

datab

-0.61

TAGE

-0.61

basicConfig

-0.57

 '*')

-0.56

\"");

-0.55

 nakalista

-0.55

 <<<<<<<<<<<<<<

-0.55

CodeDom

-0.55

POSITIVE LOGITS

exitRule

0.57

Duc

0.57

 ['./

0.53

 PropTypes

0.50

ConstraintMaker

0.49

勿

0.48

 important

0.47

不可

0.47

եր

0.47

 final

0.46

Activations Density 0.268%

gibberish. It activates on parts of words in foreign languages, seemingly random collections of letters, and numbers. It also activates on "funds."

No Known Activations