INDEX

Explanations

words and phrases suggesting progress or benefits

oai_token-act-pair · gemini-2.0-flash

Creating positive change

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

EndGlobalSection

-0.62

mobileqq

-0.56

ագրություններ

-0.56

̍

-0.54

 المعيارى

-0.54

IndentedString

-0.52

 saites

-0.52

 '\\;'

-0.52

 мәкал

-0.49

 ComVisible

-0.48

POSITIVE LOGITS

出版年

0.61

 hjemme

0.58

Kaieteur

0.56

لكتر

0.56

AddTagHelper

0.54

andina

0.54

ligg

0.53

 estimés

0.53

 Brind

0.53

brainly

0.53

Activations Density 10.472%

words and phrases suggesting progress or benefits

Creating positive change

No Comments

No Known Activations