INDEX

Explanations

names of people, brands, and organizations, as well as place names

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Wikimedijinoj

-0.66

 CreateTagHelper

-0.63

 continúas

-0.57

atase

-0.56

UH

-0.56

corrhi

-0.56

 Tole

-0.55

:✨

-0.55

 مشين

-0.55

ladel

-0.54

POSITIVE LOGITS

<bos>

2.27

0.45

 Meksiku

0.45

合わせて

0.44

had

0.43

the

0.43

0.42

ところです

0.42

 Paglinawan

0.41

Activations Density 0.769%

names of people, brands, and organizations, as well as place names

No Comments

No Known Activations