INDEX

Explanations

words and phrases related to software development, testing, and configuration

oai_token-act-pair · gemini-2.0-flash

configuring settings

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

ITECH

-0.59

 चीज़ों

-0.56

 Arles

-0.53

 Mercurio

-0.52

Obrázky

-0.51

unknownFields

-0.50

 científicos

-0.49

aarrggbb

-0.49

OGND

-0.48

itinéraire

-0.48

POSITIVE LOGITS

 MainAxisSize

0.51

 кӀ

0.50

encies

0.49

AntiForgeryToken

0.49

UIControlState

0.48

cipitation

0.48

usercontent

0.47

das

0.47

magyar

0.47

udic

0.47

Activations Density 5.359%

words and phrases related to software development, testing, and configuration

configuring settings

No Comments

No Known Activations