INDEX

Explanations

references to specific religious texts/people

oai_token-act-pair · gemini-2.0-flash

religious quotes and text

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

 kasarigan

-0.64

RenderAtEndOf

-0.62

 autorytatywna

-0.57

 HasFactory

-0.56

 defaultstate

-0.56

Personendaten

-0.54

IntentFilter

-0.54

utnant

-0.53

vård

-0.50

 дописавши

-0.50

POSITIVE LOGITS

AsUp

0.68

DoubleQuotes

0.56

UnitTesting

0.54

 Stand

0.50

 stand

0.50

 <>",

0.49

Po

0.48

illée

0.46

callee

0.46

Hochspringen

0.46

Activations Density 0.198%

references to specific religious texts/people

religious quotes and text

No Comments

No Known Activations