INDEX

Explanations

words and phrases related to sight and appearance

oai_token-act-pair · gemini-2.0-flash

look

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 nahilalakip

-0.52

 lamella

-0.52

 eventId

-0.51

 columnIndex

-0.50

 excitations

-0.48

 selectivity

-0.48

 Kamil

-0.47

 anhyd

-0.47

 izvē

-0.46

 individualism

-0.45

POSITIVE LOGITS

 Мексичка

0.78

sidemargin

0.73

 Roskov

0.67

 Biôgrafia

0.64

eleste

0.63

ViewFeatures

0.61

kloped

0.60

клопе

0.59

исленность

0.59

تقاوى

0.59

Activations Density 1.083%

words and phrases related to sight and appearance

look

No Comments

No Known Activations