INDEX

Explanations

language related to commerce and energy

oai_token-act-pair · gemini-2.0-flash

very large

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

GIVEREF

-0.74

addCriterion

-0.69

XmlAccessorType

-0.67

 initComponents

-0.63

 continúas

-0.63

HomeAsUpEnabled

-0.62

 समीक्षाओं

-0.62

TagMode

-0.60

abstractmethod

-0.59

webElementXpaths

-0.59

POSITIVE LOGITS

 giant

0.94

 mega

0.88

 gigantic

0.87

 super

0.84

 colossal

0.83

giant

0.80

meg

0.79

 Giant

0.78

 huge

0.77

 enormous

0.77

Activations Density 1.745%

language related to commerce and energy

very large

No Comments

No Known Activations