INDEX

Explanations

cooking recipes, especially methods, temperatures, and ingredients

oai_token-act-pair · gemini-2.0-flash

cooking

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

chle

-0.49

jualan

-0.45

امد

-0.42

cepatan

-0.42

กิน

-0.41

tighets

-0.41

CLUDE

-0.41

 Gesells

-0.41

ropia

-0.40

 réf

-0.40

POSITIVE LOGITS

 للاسماء

0.98

abestanden

0.91

 فريبيس

0.88

RenderAtEndOf

0.87

Tembelea

0.83

IsContent

0.83

 AssemblyTitle

0.78

WriteBarrier

0.78

 Roskov

0.78

 disambiguazione

0.76

Activations Density 1.776%

cooking recipes, especially methods, temperatures, and ingredients

cooking

No Comments

No Known Activations