INDEX

Explanations

words related to hobbies, media, and entertainment

oai_token-act-pair · gemini-2.0-flash

blogs, comics, dogs

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

 متعلقه

-0.67

UserScript

-0.63

makeText

-0.55

 Wiktionnaire

-0.55

THISDAY

-0.53

 mergeFrom

-0.52

findpost

-0.51

 محفوظة

-0.50

 <=",

-0.48

tagHelperRunner

-0.48

POSITIVE LOGITS

xffffffff

0.64

Initializable

0.59

 مواليد

0.58

paravant

0.56

ratto

0.56



0.55

 person

0.55

省市镇

0.54

Manbalar

0.52

 getCategory

0.51

Activations Density 1.443%

words related to hobbies, media, and entertainment

blogs, comics, dogs

No Comments

No Known Activations