INDEX

Explanations

phrases used support an idea or praising a person

oai_token-act-pair · gemini-2.0-flash

agreeing or good points

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

 espagnole

-0.65

تفصیلات

-0.62

 كومونز

-0.61

 chré

-0.60

 ligiloj

-0.60

HostException

-0.57

 colpa

-0.57

ViewFeatures

-0.57

 دیکھیے

-0.57

 suivante

-0.56

POSITIVE LOGITS

TypedDataSet

0.58

出版年

0.56

 lenker

0.51

 poud

0.50

CrossRef

0.48

 للمعارف

0.48

<?

0.47

scriptcase

0.45

 Republics

0.44

TabIndex

0.44

Activations Density 0.853%

phrases used support an idea or praising a person

agreeing or good points

No Comments

No Known Activations