INDEX

Explanations

code that contains variable initializations and increments within loops

oai_token-act-pair · gemini-2.0-flash

=

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

importanza

-0.52

lofen

-0.49

ləş

-0.48

 betale

-0.48

 nisso

-0.48

 gestellt

-0.47

operazione

-0.46

ztály

-0.45

($)

-0.45

Schedulers

-0.44

POSITIVE LOGITS

 ***!

0.82

 defaultstate

0.73

tagHelperRunner

0.69

IndentedString

0.65

 tartalomajánló

0.58

出版年

0.57

IUrlHelper

0.57

__.__

0.55

OGND

0.54

RTSC

0.53

Activations Density 0.121%

code that contains variable initializations and increments within loops

=

No Comments

No Known Activations