INDEX

Explanations

code syntax related to multicast addresses and padding

oai_token-act-pair · gemini-2.0-flash

code snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

CloseOperation

-0.77

tagext

-0.72

 AttributeSet

-0.69

Personendaten

-0.68

AlterField

-0.63

 Commencez

-0.63

 ModelExpression

-0.62

 himſelf

-0.62

UnsafeEnabled

-0.60

UrlResolution

-0.59

POSITIVE LOGITS

Попис

0.46

Bigr

0.45

 kasarigan

0.42

RegressionTest

0.42

ricus

0.42

amerikanischer

0.41

zieży

0.39

zumaki

0.39

upiter

0.38

Activations Density 8.690%

code syntax related to multicast addresses and padding

code snippets

No Comments

No Known Activations