INDEX

Explanations

code that produces different kinds of program outputs

oai_token-act-pair · gemini-2.0-flash

computer code

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

↵↵

-0.65

↵

-0.64

ScreenState

-0.50

↵↵↵

-0.44

basicConfig

-0.44

InstanceState

-0.43

PreExecute

-0.43

ClientSize

-0.43

ByPrimaryKey

-0.39

stateParams

-0.39

POSITIVE LOGITS

 continúas

0.73

Hochspringen

0.72

 betweenstory

0.63

GEBURTSDATUM

0.63

mahaman

0.62

談社

0.59

 gynnwys

0.59

+#+#

0.59

 bezeichneter

0.58

Activations Density 4.536%

code that produces different kinds of program outputs

computer code

No Comments

No Known Activations