INDEX

Explanations

mentions of research being written and released.

oai_token-act-pair · gemini-2.0-flash

published

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

 فريبيس

-0.73

 nahilalakip

-0.66

 Reverso

-0.63

-0.58

 censiti

-0.57

hdys

-0.55

:✨

-0.54

 resourceCulture

-0.54

erçe

-0.53

 fielder

-0.51

POSITIVE LOGITS

 незавершена

0.66

 Paglinawan

0.64

XmlEnum

0.57

 chấm

0.55

ErrorResponse

0.52

DoubleQuotes

0.51

RuleContext

0.51

 الاطلاع

0.50

Carriera

0.50

ças

0.49

Activations Density 3.303%

mentions of research being written and released.

published

No Comments

No Known Activations