INDEX

Explanations

words and phrases related to ownership, copyright, and notability.

oai_token-act-pair · gemini-2.0-flash

owner/holder

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

podes

-0.53

anças

-0.52

 accesibles

-0.48

 المعيارى

-0.48

 skjer

-0.46

 ivelany

-0.46

ItemLayout

-0.45

jaciół

-0.45

ientí

-0.44

yntaxException

-0.43

POSITIVE LOGITS

 owner

2.20

 owners

2.11

owner

1.91

 Owner

1.89

Owner

1.81

 Owners

1.80

 holder

1.80

owners

1.74

 holders

1.72

Owners

1.72

Activations Density 1.049%

words and phrases related to ownership, copyright, and notability.

owner/holder

No Comments

No Known Activations