INDEX

Explanations

words related to car features and functions

oai_token-act-pair · gemini-2.0-flash

car interiors and parts

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

komp

-0.47

ulang

-0.44

orsch

-0.43

}}}

-0.43

talen

-0.42

Reload

-0.41

 cepillo

-0.41

ugan

-0.41

InInspector

-0.41

men

-0.40

POSITIVE LOGITS

الحياه

0.73

CppMethod

0.72

 HasFactory

0.67

 nahilalakip

0.63

 snippetHide

0.63

usermodel

0.63

تقاوى

0.63

ngdoc

0.62

 carpets

0.62

 AttributeSet

0.60

Activations Density 1.177%

words related to car features and functions

car interiors and parts

No Comments

No Known Activations