INDEX

Explanations

terms related to cells and their biological processes

oai_token-act-pair · gemini-2.0-flash

eating

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 autorytatywna

-0.77

 فريبيس

-0.75

 arşivlendi

-0.75

setupUi

-0.75

 تانيه

-0.74

دانشنامهٔ

-0.73

存于互联网档案馆

-0.73

ChildScrollView

-0.69

 كومونز

-0.69

Portály

-0.66

POSITIVE LOGITS

 teeth

1.11

 chewing

1.06

 Teeth

0.98

 bite

0.96

eat

0.95

 devouring

0.95

 eating

0.93

 hungry

0.92

 chewed

0.91

 chew

0.88

Activations Density 1.364%

terms related to cells and their biological processes

eating

No Comments

No Known Activations