INDEX

Explanations

a wide variety of words, many of which seem to be from some kind of science fiction show

oai_token-act-pair · gemini-2.0-flash

ashi

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Milla

-0.77

 MILL

-0.75

 Mill

-0.74

RenderAtEndOf

-0.69

Mill

-0.68

 disambiguazione

-0.66

 Millennium

-0.66

 MILLS

-0.65

Mil

-0.64

 mill

-0.63

POSITIVE LOGITS

 للاسماء

0.69

]")]

0.53

uwe

0.50

sdag

0.48

gnan

0.47

ându

0.47

èves

0.46

ViewImports

0.45

guém

0.45

 simultaneous

0.44

Activations Density 9.444%

a wide variety of words, many of which seem to be from some kind of science fiction show

ashi

No Comments

No Known Activations