INDEX

Explanations

third-person pronouns, pronouns in general, and references.

oai_token-act-pair · gemini-2.0-flash

He

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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



-0.99

esModule

-0.78

ơn

-0.68

 JAXBElement

-0.68

 defStyleAttr

-0.66

 bacterio

-0.65

 HasFactory

-0.65

Erstellt

-0.65

SPATH

-0.65

 surla

-0.62

POSITIVE LOGITS

<bos>

1.18

InitVars

0.64

Spoljašnje

0.53

NullCheck

0.48

médiaire

0.48

 kasarigan

0.47

гӀ

0.46

曖昧さ回避

0.43

.*")]

0.43

Referencie

0.43

Activations Density 2.731%

third-person pronouns, pronouns in general, and references.

He

No Comments

No Known Activations