INDEX

Explanations

terms related to medical testing and studies

oai_token-act-pair · gemini-2.0-flash

numbers

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

клопе

-0.73

WithIOException

-0.65

PORTE

-0.62

ơn

-0.62

 Motto

-0.56

NewUrlParser

-0.56

 kasarigan

-0.55

BindingSource

-0.54

 carte

-0.54

vario

-0.52

POSITIVE LOGITS

 affez

0.51

verwijspagina

0.50

tangentMode

0.50

 giudi

0.49

giaan

0.48

 keduanya

0.47

 Potosí

0.46

gdx

0.45

 médié

0.45

 buttocks

0.45

Activations Density 8.495%

terms related to medical testing and studies

numbers

No Comments

No Known Activations