INDEX

Explanations

the word "high"

oai_token-act-pair · gemini-2.0-flash

high

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

findpost

-0.84

enumii

-0.83

RuleContext

-0.79

 للاسماء

-0.77

enumi

-0.74

NewUrlParser

-0.71

ByUsername

-0.70

 photolibrary

-0.69

 незавершена

-0.69

OGND

-0.69

POSITIVE LOGITS

 class

0.65

class

0.58

end

0.57

Class

0.52

 quali

0.51

MOQ

0.47

 tech

0.43

 Schluss

0.43

 poly

0.43

 Glanz

0.42

Activations Density 0.319%

the word "high"

high

No Comments

No Known Activations

the word "high"

high

No Comments

No Known Activations