INDEX

Explanations

code snippets from Android layout XML files

oai_token-act-pair · gemini-2.0-flash

:

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits



-0.72

ItemLayout

-0.69

ApiModel

-0.67

 layui

-0.65

esez

-0.64

ंदीखरीदारी

-0.64

anmoins

-0.61

Климат

-0.60

 surla

-0.59

 AssemblyVersion

-0.57

POSITIVE LOGITS

 مرئيه

0.46

вге

0.43

 potest

0.43

出版年

0.42

 bề

0.42

]-'

0.41

 habet

0.41

meen

0.40

:✨

0.40

</thead>

0.39

Activations Density 0.305%

code snippets from Android layout XML files

:

No Comments

No Known Activations