INDEX

Explanations

markdown formatting and URLs

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_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 MenuView

-1.05

 isInitialized

-0.98

 فريبيس

-0.94

 betweenstory

-0.91

 ComVisible

-0.90

PerformLayout

-0.89

MessageTagHelper

-0.88

Personendaten

-0.88

 autorytatywna

-0.88

GIVEREF

-0.88

POSITIVE LOGITS

//

0.62

’

0.56

»

0.54

//

0.51

.’

0.51

—

0.50

0.49

0.48

<em>

0.47

/*

0.47

Activations Density 10.064%

markdown formatting and URLs

](

No Comments

No Known Activations