INDEX

Explanations

instances of "built-in" and words that are often associated with the description of electronics.

oai_token-act-pair · gemini-2.0-flash

in

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 مشين

-0.88

elemField

-0.79

 wireType

-0.75

 ویکی‌پدیای

-0.74

:✨

-0.70

UnsafeEnabled

-0.68

tagext

-0.68

Rüyada

-0.66

 AssemblyCulture

-0.64

 Roskov

-0.62

POSITIVE LOGITS

<bos>

0.60

kova

0.52

 الحره

0.51

 hierfür

0.50

 specialized

0.47

 specialize

0.46

 Hooper

0.46

 réputation

0.46

nin

0.45

,:);

0.45

Activations Density 3.457%

instances of "built-in" and words that are often associated with the description of electronics.

in

No Comments

No Known Activations