INDEX

Explanations

code snippets and technical jargon related to computer programming and networking

oai_token-act-pair · gemini-2.0-flash

code/technical support

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

endphp

-0.83

]")]

-0.74

بوابة

-0.70

/>";

-0.68

BufferException

-0.66

?”,

-0.65

*/,

-0.65

GraphicsUnit

-0.63

참고

-0.63

 članak

-0.63

POSITIVE LOGITS

Your

0.57

 inderdaad

0.54

 your

0.53

 Your

0.52

your

0.50

 éditoriale

0.49

0.47

you

0.47

 IIRC

0.47

engagent

0.46

Activations Density 4.241%

code snippets and technical jargon related to computer programming and networking

code/technical support

No Comments

No Known Activations