INDEX

Explanations

the word "Sun", and sometimes the name "Smith"

oai_token-act-pair · gemini-2.0-flash

sun

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

RegressionTest

-0.64

UnusedPrivate

-0.62

ObjectContext

-0.62

Jeografia

-0.60

complexType

-0.59

HttpFoundation

-0.59

MemoryWarning

-0.57

invokeLater

-0.56

DeleteBehavior

-0.56

 createContext

-0.56

POSITIVE LOGITS

taza

0.59

DockStyle

0.57

PDI

0.56

0.52

glasses

0.50

NewLabel

0.50

 glasses

0.49

цездатний

0.48

powder

0.48

partimento

0.48

Activations Density 0.853%

the word "Sun", and sometimes the name "Smith"

sun

No Comments

No Known Activations