INDEX

Explanations

code snippets intermixed with natural language.

oai_token-act-pair · gemini-2.0-flash

Foreign languages

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 المعيارى

-0.73

StoryboardSegue

-0.68

Tikang

-0.65

 utafitiHapana

-0.64

 الحره

-0.61

MigrationBuilder

-0.61

 beginnetje

-0.60

참고

-0.60

verwijspagina

-0.60

})*/

-0.59

POSITIVE LOGITS

interopRequire

0.44

vyšší

0.44

GIVEREF

0.44

si

0.44

bedded

0.43

ProgressHUD

0.42

letterSpacing

0.42

 setTimeout

0.42

 Reserv

0.41

yok

0.41

Activations Density 1.335%

code snippets intermixed with natural language.

Foreign languages

No Comments

No Known Activations