INDEX

Explanations

words suggesting things that happen, can be changed, or are ongoing

oai_token-act-pair · gemini-2.0-flash

changes in circumstances

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 Paglinawan

-0.65

tvguidetime

-0.62

 raisins

-0.58

 Dutt

-0.58

 समीक्षक

-0.57

 walnuts

-0.57

scrapy

-0.56

 Rouge

-0.56

 newData

-0.56

 Italijani

-0.56

POSITIVE LOGITS

Portail

0.52

isNameExpr

0.49

DockStyle

0.48

tagHelperRunner

0.45

 MainAxisSize

0.45

PreferredItem

0.44

越好

0.44

arXiv

0.43

دانشنامهٔ

0.43

OGND

0.43

Activations Density 2.572%

words suggesting things that happen, can be changed, or are ongoing

changes in circumstances

No Comments

No Known Activations