INDEX

Explanations

programming terms, especially code-related questions using variables

oai_token-act-pair · gemini-2.0-flash

programming code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

is

-1.26

can

-0.86

has

-0.80

are

-0.80

was

-0.78

may

-0.70

isn

-0.69

 είναι

-0.69

 will

-0.68

IsContent

-0.65

POSITIVE LOGITS

 CreateTagHelper

0.58

)++;

0.49

quitous

0.48

ftagPool

0.46

 BrowserRouter

0.46

]<<

0.43

deko

0.40

hagic

0.40

SPATH

0.40

 olvides

0.40

Activations Density 0.778%

programming terms, especially code-related questions using variables

programming code

No Comments

No Known Activations