INDEX

Explanations

code, probably Java or Objective-C

oai_token-act-pair · 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

makeConstraints

-0.82

ⓧ

-0.82

TemporalType

-0.79

WithMany

-0.75

Personendaten

-0.74

setVerticalGroup

-0.73

InputBorder

-0.72

NameInMap

-0.71

bitField

-0.71

MemoryWarning

-0.69

POSITIVE LOGITS

<bos>

0.50

庁

0.45

execSQL

0.44

denly

0.42

#!/

0.41

One

0.40

ział

0.40

$_['

0.40

benzene

0.39

Activations Density 5.026%

code, probably Java or Objective-C

No Comments

No Known Activations