INDEX

Explanations

language related to research, growth projections, and government agencies

oai_token-act-pair · gemini-2.0-flash

expectations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 expected

-0.65

 expect

-0.61

 prevé

-0.60

 anticipated

-0.60

 verwacht

-0.59

 previsão

-0.57

expected

-0.56

预计

-0.55

 predict

-0.54

 predicted

-0.54

POSITIVE LOGITS

](#

0.63

Brainz

0.59

ViewImports

0.56

 חיצוניים

0.56

Necesito

0.54

newtheorem

0.54

manos

0.50

pédie

0.50

wahati

0.48

ugc

0.48

Activations Density 25.008%

language related to research, growth projections, and government agencies

expectations

No Comments

No Known Activations