INDEX

Explanations

mentions about space, followed by industrial processes for the first half then it switches to finding mentions of manufacturers.

oai_token-act-pair · gemini-2.0-flash

technical documents

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

protoimpl

-0.68

 uVar

-0.50

 dzī

-0.49

axel

-0.49

ArrowToggle

-0.49

 chinoise

-0.48

 vostri

-0.48

 MenuView

-0.48

 laikā

-0.47

InsertCommand

-0.47

POSITIVE LOGITS

 Мексичка

0.63

]--;

0.63

.*")]

0.62

MENAFN

0.56

roek

0.56

Javadoc

0.56

:][

0.54

Попис

0.53

bited

0.52

WriteTagHelper

0.51

Activations Density 1.376%

mentions about space, followed by industrial processes for the first half then it switches to finding mentions of manufacturers.

technical documents

No Comments

No Known Activations