INDEX

Explanations

personal narratives about past experiences

oai_token-act-pair · gemini-2.0-flash

About activities and going places

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

="@+

-0.50

sscanf

-0.49

ванович

-0.48

Hrsg

-0.47

bal

-0.46

 dataSnapshot

-0.45

寄せ

-0.44

izielle

-0.43

viewDid

-0.42

VID

-0.42

POSITIVE LOGITS

脚注の使い方

0.72

awtextra

0.68

 الرياضيه

0.65

#+#

0.63

 TestBed

0.62

íncia

0.62

Välislingid

0.61

 دیکھیے

0.61

AddHtmlAttribute

0.60

IntoConstraints

0.58

Activations Density 1.405%

personal narratives about past experiences

About activities and going places

No Comments

No Known Activations