INDEX

Explanations

references to people interacting with each other

oai_token-act-pair · gemini-2.0-flash

people

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

who

-0.98

who

-0.91

Who

-0.79

whom

-0.71

Who

-0.71

 whom

-0.70

WHO

-0.64

WHO

-0.63

 Whom

-0.62

Kdo

-0.60

POSITIVE LOGITS

脚注の使い方

0.67

ьаж

0.67

IsMutable

0.66

Revenir

0.59

 referrerpolicy

0.56

PasswordEncoder

0.54

новниш

0.53

 Baillargeon

0.53

’

0.52

Története

0.51

Activations Density 15.327%

references to people interacting with each other

people

No Comments

No Known Activations