INDEX

Explanations

conjunctions and related words

oai_token-act-pair · gemini-2.0-flash

research/technical writing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

ugía

-0.57

 EdgeInsets

-0.57

Vidite

-0.55

icef

-0.52

sī

-0.52

XtraEditors

-0.52

HasAnnotation

-0.52

ⓧ

-0.52

Hochspringen

-0.51

FXML

-0.50

POSITIVE LOGITS

Autoritní

0.63

featureID

0.60

URLException

0.54

indd

0.52

ImageContext

0.50

OrNil

0.49

TagMode

0.47

GEBURTSDATUM

0.45

 contextLoads

0.44

sequently

0.43

Activations Density 1.452%

conjunctions and related words

research/technical writing

No Comments

No Known Activations