INDEX

Explanations

Java code imports and library classes

oai_token-act-pair · gemini-2.0-flash

Linq or List

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

 mergeFrom

-0.56

 beginnetje

-0.54

here

-0.50

expandindo

-0.49

гар

-0.48

Linq

-0.48

 चीज़ों

-0.46

each

-0.46

fe

-0.45

IVEREF

-0.45

POSITIVE LOGITS

">—

0.62

erdings

0.60

tvguidetime

0.59

urro

0.57

 Gutenberg

0.56

^(@)

0.56

discuss

0.55

prefixer

0.55

sieur

0.55

unesse

0.54

Activations Density 0.068%

Java code imports and library classes

Linq or List

No Comments

No Known Activations