INDEX

Explanations

code, code commands and flags, and references to versions

oai_token-act-pair · gemini-2.0-flash

-

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

matchCondition

-0.69

 ویکی‌پدیای

-0.60

EndInit

-0.60

AddTagHelper

-0.59

UnsafeEnabled

-0.57

 تضيفلها

-0.55

 Wicidata

-0.54

HasForeignKey

-0.52

ỗi

-0.52

urgy

-0.52

POSITIVE LOGITS

nthetic

0.56

0.50

hs

0.48

程度

0.48

parsedMessage

0.47

perative

0.47

 domenica

0.46

Horizontal

0.46

外部連結

0.46

RVA

0.46

Activations Density 0.610%

code, code commands and flags, and references to versions

-

No Comments

No Known Activations