INDEX

Explanations

place names and locations.

oai_token-act-pair · gemini-2.0-flash

Locations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

^(@

-0.56

AddTagHelper

-0.51

ároz

-0.51

yarnpkg

-0.50

kunta

-0.48

izard

-0.48

AppCompatTheme

-0.48

 lccn

-0.47

^(@)

-0.47

IsMutable

-0.47

POSITIVE LOGITS

 ExecuteAsync

0.68

Carriera

0.58

>>=

0.55

ranet

0.55

expandindo

0.54

 privatisation

0.54

findpost

0.51

 chieftain

0.49

 kaynağından

0.49

 raider

0.48

Activations Density 1.020%

place names and locations.

Locations

No Comments

No Known Activations