INDEX

Explanations

mailing addresses

oai_token-act-pair · gemini-2.0-flash

Addresses or IDs

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 betweenstory

-0.99

 lenker

-0.97

 autorytatywna

-0.97

 Administrativna

-0.90

ConstraintMaker

-0.89

 فريبيس

-0.89

ValueStyle

-0.89

AnimationsModule

-0.86

 unknownFields

-0.83

 ویکی‌پدی

-0.83

POSITIVE LOGITS

th

0.47

0.45

0.44

0.42

kovich

0.41

0.40

 Union

0.40

All

0.40

Activations Density 1.041%

mailing addresses

Addresses or IDs

No Comments

No Known Activations