INDEX

Explanations

code examples, especially related to software and classes

oai_token-act-pair · gemini-2.0-flash

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

XmlAccessorType

-0.47

 rowspan

-0.45

ummer

-0.44

(*(

-0.43

 noemen

-0.43

 tarko

-0.42

 lets

-0.41

<$

-0.41

 transferred

-0.41

zeb

-0.40

POSITIVE LOGITS

TestBed

0.71

elemField

0.65

OGND

0.65

SharedCtor

0.64

 BrowserModule

0.64

 TestBed

0.64

plish

0.63

 autorytatywna

0.63

GEBURTSDATUM

0.62

 ProtoMessage

0.60

Activations Density 18.928%

code examples, especially related to software and classes

code

No Comments

No Known Activations