INDEX

Explanations

LaTeX commands and math symbols

oai_token-act-pair · gemini-2.0-flash

operatorname

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

どもの

-0.56

脚注の使い方

-0.50

Geographie

-0.50

 Danville

-0.50

 المعيارى

-0.50

 Comstock

-0.50

 prada

-0.49

guous

-0.49

duled

-0.49

 vena

-0.49

POSITIVE LOGITS

 الحره

0.65

BeginContext

0.59

 ComVisible

0.58

#+#

0.56

 protoimpl

0.55

kloped

0.55



0.54

WebElementEntity

0.53

ReusableCell

0.52

WebVitals

0.51

Activations Density 2.834%

LaTeX commands and math symbols

operatorname

No Comments

No Known Activations