INDEX

Explanations

dates

oai_token-act-pair · gemini-2.0-flash

say ","

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

TagMode

-0.97

 EconPapers

-0.91

findpost

-0.83

 المعيارى

-0.81

 ddelweddau

-0.80

AndEndTag

-0.78

ReusableCell

-0.75

IntoConstraints

-0.74

 AssemblyCompany

-0.73

حياتها

-0.69

POSITIVE LOGITS

1.48

0.53

،

0.43

shadowRadius

0.42

，

0.42

 iprot

0.41

,,

0.38

?,

0.35

ifstream

0.35

_,

0.35

Activations Density 2.937%

dates

say ","

No Comments

No Known Activations