INDEX

Explanations

location-related terms, like dominated areas and places

oai_token-act-pair · gemini-2.0-flash

geographical locations

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

sizePolicy

-0.47

 resourceCulture

-0.41

MemoryWarning

-0.40

 CommonModule

-0.40

 persons

-0.40

 Screen

-0.40

 kasarigan

-0.39

person

-0.39

ScreenState

-0.39

 gente

-0.38

POSITIVE LOGITS

 propOrder

0.75

-------------</

0.69

LookAnd

0.67

ferrous

0.63

 JAXB

0.61

المكان

0.61

:✨

0.61

----</

0.60

IndentedString

0.60

 transfieras

0.60

Activations Density 0.361%

location-related terms, like dominated areas and places

geographical locations

No Comments

No Known Activations