INDEX

Explanations

acronyms that are likely abbreviations

oai_token-act-pair · gemini-2.0-flash

science

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 beider

-0.49

hyrchwyd

-0.48

 entrambi

-0.46

 Both

-0.46

FOOTNOTES

-0.45

+][

-0.44

 Đông

-0.44

zubauen

-0.43

Carriera

-0.43

Ambos

-0.43

POSITIVE LOGITS

XmlAccessorType

0.69

MLLoader

0.67

IMPORTED

0.60

ScopeManager

0.57

GraphicsUnit

0.57

InjectAttribute

0.56

DoubleQuotes

0.55

PMailer

0.54

ModelSerializer

0.49

moveToFirst

0.49

Activations Density 1.207%

acronyms that are likely abbreviations

science

No Comments

No Known Activations