INDEX

Explanations

code-related snippets

oai_token-act-pair · gemini-2.0-flash

Code and programming snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

XmlAccessorType

-0.65

archar

-0.55

мум

-0.54

NAM

-0.53

hamed

-0.51

portál

-0.49

ilyen

-0.48

omials

-0.48

SaveSave

-0.48

Tikang

-0.47

POSITIVE LOGITS

StackNavigator

0.59

LayoutStyle

0.56

featureID

0.53

yorsunuz

0.53

ActionCreators

0.52

UnusedPrivate

0.50

chappement

0.49

huber

0.49

ListFragment

0.49

RetentionPolicy

0.48

Activations Density 6.361%

code-related snippets

Code and programming snippets

No Comments

No Known Activations