INDEX

Explanations

research citations or references to figures and tables

oai_token-act-pair · gemini-2.0-flash

say "number 1"

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WireFormatLite

-0.44

-0.43

lastIndexOf

-0.42

__':

-0.41

WillAppear

-0.41

asy

-0.40

ਅ

-0.38

 huit

-0.38

OutputType

-0.38

POSITIVE LOGITS

0.80

১

0.68

 surla

0.67

ukone

0.65

 OFDb

0.65

１

0.65

₁(

0.64

 Eleventh

0.63

१

0.62

 дописавши

0.59

Activations Density 2.511%

research citations or references to figures and tables

say "number 1"

No Comments

No Known Activations