INDEX

Explanations

program code and related programming jargon in technical writing, as well as corporate-speak buzzwords.

oai_token-act-pair · gemini-2.0-flash

The word "once"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 Chwiliwch

-0.78

 المعيارى

-0.73

 متعلقه

-0.69

saraba

-0.64

 StatelessWidget

-0.62

rungsseite

-0.60

šanai

-0.59

})();

-0.59

">//

-0.58

RefNanny

-0.57

POSITIVE LOGITS

 once

3.95

once

3.53

Once

3.28

 Once

3.25

 ONCE

2.94

ONCE

2.77

 einmal

1.75

 sekali

1.58

一旦

1.40

一度

1.34

Activations Density 14.179%

program code and related programming jargon in technical writing, as well as corporate-speak buzzwords.

The word "once"

No Comments

No Known Activations