INDEX

Explanations

capitalized words and acronyms, especially names and initialisms.

oai_token-act-pair · gemini-2.0-flash

Question answering/articles

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

mybatisplus

-0.79

EndInit

-0.75

 initComponents

-0.71

Jeografia

-0.71

 للمعارف

-0.71

Искәрмәләр

-0.70

 viewDidLoad

-0.70

 EconPapers

-0.70

IsContent

-0.68

unitOfWork

-0.68

POSITIVE LOGITS

 Alegre

0.49

 flamengo

0.48

 favorable

0.47

 favourable

0.47

↵

0.47

 Senhora

0.46

 Reverso

0.45

ゞ

0.45

YPTO

0.45

YGON

0.45

Activations Density 3.799%

capitalized words and acronyms, especially names and initialisms.

Question answering/articles

No Comments

No Known Activations