INDEX

Explanations

text having to do with specific real-world events including dates, times, and locations

oai_token-act-pair · gemini-2.0-flash

Random assortment of text

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للمعارف

-0.57

,:);

-0.56

تقاوى

-0.56

]")]

-0.53

 FontWeight

-0.53

oredCriteria

-0.53

<?

-0.52

endphp

-0.52

XmlRootElement

-0.50

 JpaRepository

-0.50

POSITIVE LOGITS

出版年

0.65

 esternos

0.50

weist

0.49

 مؤرشف

0.48

 faute

0.46

wold

0.45

utations

0.45

haya

0.45

oteca

0.45

udios

0.45

Activations Density 0.521%

text having to do with specific real-world events including dates, times, and locations

Random assortment of text

No Comments

No Known Activations