INDEX

Explanations

citations of academic papers

oai_token-act-pair · gemini-2.0-flash

citations

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

-0.81

InputBorder

-0.73

 autorytatywna

-0.70

NameInMap

-0.69

دانشنامهٔ

-0.67

UnusedPrivate

-0.66

AndEndTag

-0.63

/**

-0.63

expandindo

-0.63

 كومونز

-0.62

POSITIVE LOGITS

 Vikipedi

0.54

uttg

0.51

 Penh

0.47

եց

0.47

newcommand

0.46

⁃

0.46

witzerland

0.46

pagestyle

0.45

Serde

0.45

up

0.45

Activations Density 7.055%

citations of academic papers

citations

No Comments

No Known Activations