INDEX

Explanations

words associated with mathematical decay, functions, and data

oai_token-act-pair · gemini-2.0-flash

rates of change

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 mergeFrom

-0.66

RegressionTest

-0.59

writeFieldEnd

-0.56

kenstock

-0.54

 دیکھیے

-0.52

涯

-0.52

aarrggbb

-0.51

overflow

-0.51

flashdata

-0.49

 peau

-0.48

POSITIVE LOGITS

TemporalType

0.60

Gemeinden

0.56

ChildScrollView

0.55

 endwhile

0.52

AutoScale

0.51

ViewFeatures

0.50

 Audiodateien

0.50

gable

0.49

MemoryWarning

0.48

RectangleBorder

0.48

Activations Density 2.304%

words associated with mathematical decay, functions, and data

rates of change

No Comments

No Known Activations