INDEX

Explanations

words related to scientific experimental processes involving masking and shortening

oai_token-act-pair · gemini-2.0-flash

Reduction, cutting, or ignoring

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

NgModule

-0.55

MathML

-0.55

Xna

-0.53

poti

-0.52

]})

-0.51

endphp

-0.49

])->

-0.48

AnchorStyles

-0.48

aku

-0.48

 ioutil

-0.47

POSITIVE LOGITS

SharedCtor

0.70

kloped

0.64

GEBURTSDATUM

0.63

SharedDtor

0.63

Diwedd

0.59

@"/

0.57

σθαι

0.56

 leſs

0.56

 roulant

0.56

MessageTagHelper

0.54

Activations Density 6.034%

words related to scientific experimental processes involving masking and shortening

Reduction, cutting, or ignoring

No Comments

No Known Activations