INDEX

Explanations

technical language used in legal or scientific contexts.

oai_token-act-pair · gemini-2.0-flash

legal/question/code contexts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-0.76

 StringTokenizer

-0.61

ArgumentParser

-0.59

CWE

-0.57

 SDLK

-0.57

XDECREF

-0.55

fromnode

-0.53

 Wikisource

-0.53

 circonstances

-0.53

ustomed

-0.53

POSITIVE LOGITS

 مرئيه

0.61

تقاوى

0.46

strix

0.45

🏻‍♀️

0.44

หน้านี้

0.44

wuchs

0.44

*/;

0.44

новништво

0.43

μος

0.43

lső

0.43

Activations Density 18.806%

technical language used in legal or scientific contexts.

legal/question/code contexts

No Comments

No Known Activations