INDEX

Explanations

code diffs or comments, and filenames

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_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

OGND

-0.79

rovnik

-0.73

Tembelea

-0.70

IsContent

-0.67

بوابة

-0.66

LayoutPanel

-0.65

gages

-0.63

 AttributeSet

-0.61

Portale

-0.59

ItemBackground

-0.59

POSITIVE LOGITS

Pij

0.43

İstinadlar

0.42

mAdapter

0.40

مراجع

0.40

dası

0.39

CGContext

0.39

 Cama

0.38

gemeen

0.37

snake

0.36

 dự

0.36

Activations Density 0.139%

code diffs or comments, and filenames

say "-"

No Comments

No Known Activations