INDEX

Explanations

sentences that suggest the subject is functioning as intended

oai_token-act-pair · gemini-2.0-flash

Things working as intended

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 المعيارى

-0.75

 урна

-0.72

 للاسماء

-0.69

SequentialGroup

-0.59

::::::::

-0.58

 nakalista

-0.58

 فريبيس

-0.57

 للمعارف

-0.57

zielle

-0.56

parsedMessage

-0.56

POSITIVE LOGITS

 when

0.62

 quando

0.52

الحياه

0.50

 WHEN

0.49

ByPrimaryKey

0.49

 sunshine

0.48

OrCreate

0.48

when

0.48

 cuándo

0.47

 lorsque

0.47

Activations Density 2.904%

sentences that suggest the subject is functioning as intended

Things working as intended

No Comments

No Known Activations