INDEX

Explanations

words in the context of vehicles, their performance, and components like brakes and gears

oai_token-act-pair · gemini-2.0-flash

vehicle performance

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 propOrder

-0.86

ImageContext

-0.82

IContainer

-0.81

ScopeManager

-0.68

 Jocelyn

-0.67

 урна

-0.66

 الرياضيه

-0.66

hopped

-0.66

 Euri

-0.64

labus

-0.64

POSITIVE LOGITS

roli

0.41

 program

0.40

gam

0.39

ght

0.39

.:

0.39

原始内容存档

0.37

GAM

0.36

נה

0.36

ini

0.36

 principal

0.35

Activations Density 2.399%

words in the context of vehicles, their performance, and components like brakes and gears

vehicle performance

No Comments

No Known Activations