INDEX

Explanations

names of countries and organizations, particularly those related to chess

oai_token-act-pair · gemini-2.0-flash

chess

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PhysRevLett

-0.69

TintMode

-0.57

nonatomic

-0.54

出版年

-0.50

 CreateTagHelper

-0.49

สน

-0.48

asibility

-0.47

 ***!

-0.46

AndEndTag

-0.46

 sfer

-0.45

POSITIVE LOGITS

AnchorTagHelper

0.66

mybatisplus

0.62

 архивлан

0.58

 كومونز

0.56

devise

0.54

GLint

0.54

 defeat

0.52

glVertex

0.52

Personensuche

0.49

Cz

0.49

Activations Density 0.935%

names of countries and organizations, particularly those related to chess

chess

No Comments

No Known Activations