INDEX

Explanations

language related to social and political issues like abortion and justice

oai_token-act-pair · gemini-2.0-flash

political/moral issues

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ंदीखरीदारी

-0.85

WithIOException

-0.73

 ModelExpression

-0.71

GEBURTSDATUM

-0.69

ControllerAdvice

-0.69

WriteTagHelper

-0.68

 propOrder

-0.68

 Biôgrafia

-0.68

vician

-0.67

 intptr

-0.66

POSITIVE LOGITS

 nobre

0.50

alach

0.50

 laws

0.46

 профиль

0.46

áni

0.44

IContainer

0.44

 malade

0.44

בס

0.44

uum

0.44

 reyes

0.44

Activations Density 4.246%

language related to social and political issues like abortion and justice

political/moral issues

No Comments

No Known Activations