INDEX

Explanations

terminology related to optical measurement and microscopy

oai_token-act-pair · gemini-2.0-flash

lasers and optical imaging

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 AttributeSet

-0.66

 nakalista

-0.59

makeConstraints

-0.57

endpush

-0.56

GEBURTSDATUM

-0.55

ChildScrollView

-0.54

GOTREF

-0.52

bitField

-0.51

 NSCoder

-0.51

setupUi

-0.49

POSITIVE LOGITS

 Roskov

0.52

 elé

0.50

Bleeding

0.49

 Reak

0.48

 compositeur

0.48

Driven

0.48

 Treiber

0.48

ILayout

0.47

stå

0.46

 drivers

0.46

Activations Density 6.246%

terminology related to optical measurement and microscopy

lasers and optical imaging

No Comments

No Known Activations