INDEX

Explanations

the word "low"

oai_token-act-pair · gemini-2.0-flash

low

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

Low

-0.80

low

-0.79

Low

-0.71

InitStruct

-0.65

pyplot

-0.65

 lowest

-0.62

 низ

-0.60

IntoConstraints

-0.59

npos

-0.59

 lower

-0.59

POSITIVE LOGITS

 Daß

0.59

󠁢

0.56

évaluateur

0.53

 Lala

0.48

 istore

0.46

FAP

0.45

land

0.45

RegressionTest

0.45

 Maak

0.44

 noDo

0.43

Activations Density 1.893%

the word "low"

low

No Comments

No Known Activations