INDEX

Explanations

code snippets, especially in languages like C++, Java, or Pascal, with emphasis on variable declarations, addressing, or method definitions related to printing or assigning numbers.

oai_token-act-pair · gemini-2.0-flash

punctuation

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

Negative Logits

^(@)

-1.32

MigrationBuilder

-1.29

$_"

-1.26

ViewFeatures

-1.25

دانشنامهٔ

-1.22

adpleegd

-1.21

BibitemShut

-1.21

 myſelf

-1.16

 ―――――

-1.14

Efq

-1.14

POSITIVE LOGITS

“

0.49

0.48

0.46

...

0.43

0.42

0.40

‘

0.40

Activations Density 12.390%

code snippets, especially in languages like C++, Java, or Pascal, with emphasis on variable declarations, addressing, or method definitions related to printing or assigning numbers.

punctuation

No Known Activations

code snippets, especially in languages like C++, Java, or Pascal, with emphasis on variable declarations, addressing, or method definitions related to printing or assigning numbers.

punctuation

No Known Activations