INDEX

Explanations

the word "at" with some other words nearby

oai_token-act-pair · gemini-2.0-flash

at

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

adpleegd

-0.49

migrationBuilder

-0.48

Thema

-0.45

erton

-0.44

出版年

-0.43

 справ

-0.43

 pinulongan

-0.43

 haram

-0.43

knecht

-0.43

 "','

-0.41

POSITIVE LOGITS

ViewImports

0.68

DoubleQuotes

0.65

 ddelweddau

0.61

setof

0.61

webElement

0.58

іод

0.58

########.

0.57

MLLoader

0.57

 Paglinawan

0.56

</thead>

0.54

Activations Density 0.544%

the word "at" with some other words nearby

at

No Comments

No Known Activations