INDEX

Explanations

words and phrases associated with forms and data entry

oai_token-act-pair · gemini-2.0-flash

code and text entry

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

ArgumentParser

-0.72

GEBURTSDATUM

-0.70

UrlEncoded

-0.67

enderror

-0.66

 ModelExpression

-0.65

FormState

-0.61

 VIAF

-0.60

urlencoded

-0.59

ManagedBean

-0.59

 FormBuilder

-0.58

POSITIVE LOGITS

pozorn

0.52

 achtergrond

0.52

overset

0.47

уза

0.47

overhead

0.45

 estran

0.45

MEASURE

0.44

MERCE

0.44

 delan

0.44

 Aussagen

0.44

Activations Density 2.264%

words and phrases associated with forms and data entry

code and text entry

No Comments

No Known Activations