INDEX

Explanations

internet-related words and phrases, like URLs, websites, and web banners

oai_token-act-pair · gemini-2.0-flash

website design

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 OnTriggerEnter

-0.52

 NSCoder

-0.47

 intelligente

-0.44

psia

-0.41

 kapit

-0.41

 papà

-0.41

 universelle

-0.41

=*/

-0.40

 Bering

-0.40

handles

-0.40

POSITIVE LOGITS

Jeografia

0.81

 متعلقه

0.75

 AssemblyCulture

0.68

Geplaatst

0.68

+#+#

0.68

CodeAttribute

0.65

LLocation

0.64

":[{

0.64

 архивлан

0.64

 rhestr

0.63

Activations Density 0.769%

internet-related words and phrases, like URLs, websites, and web banners

website design

No Comments

No Known Activations