INDEX

Explanations

religious language

oai_token-act-pair · gemini-2.0-flash

churches

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

 church

-2.19

 Church

-2.13

 CHURCH

-2.06

Church

-2.03

church

-1.91

 churches

-1.80

 Christian

-1.76

CHURCH

-1.72

 Churches

-1.70

Christian

-1.64

POSITIVE LOGITS

IntoConstraints

0.76

 disambiguazione

0.62

 CreateTagHelper

0.60

 تضيفلها

0.59

tagHelperRunner

0.58

verifyException

0.56

InputBorder

0.56

inSlope

0.54

 NSCoder

0.54

 خارجية

0.53

Activations Density 1.471%

religious language

churches

No Comments

No Known Activations