INDEX

Explanations

snippets of code

oai_token-act-pair · gemini-2.0-flash

response

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

Obrázky

-0.85

 يتيمه

-0.81

ArgsConstructor

-0.73

 مرئيه

-0.72

 متعلقه

-0.71

SPATH

-0.71

mappedBy

-0.70

ValueStyle

-0.69

 مواليد

-0.69

")));

-0.69

POSITIVE LOGITS

code

0.51

pot

0.48

 kraj

0.48

body

0.48

 bodys

0.46

ala

0.45

Note

0.44

Fill

0.44

Body

0.43

 paces

0.43

Activations Density 8.037%

snippets of code

response

No Comments

No Known Activations