INDEX

Explanations

references to published academic works, including journal names, publishers, and editors

oai_token-act-pair · gemini-2.0-flash

citations and references

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

<bos>

-0.59

apimachinery

-0.50

Kaynakça

-0.46

argento

-0.42

 shooting

-0.41

onan

-0.41

setGeometry

-0.41

alanya

-0.39

ofed

-0.39

 sûr

-0.39

POSITIVE LOGITS

MLLoader

0.75

//

0.71

 تضيفلها

0.65

)}</

0.65

出版年

0.65

CppMethod

0.63

 MaterialApp

0.62

WriteTagHelper

0.62

/*

0.60

 CanadaChoose

0.60

Activations Density 1.206%

references to published academic works, including journal names, publishers, and editors

citations and references

No Comments

No Known Activations