INDEX

Explanations

C++ code snippets and file paths

oai_token-act-pair · gemini-2.0-flash

Non-English words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

cit

-0.50

ungi

-0.48

//

-0.46

 fatal

-0.45

)]:

-0.43

 Pages

-0.42

 dingin

-0.42

]]:

-0.41

DET

-0.41

mení

-0.40

POSITIVE LOGITS

 المعيارى

0.80

 صوتيه

0.79

帖最后由

0.78

expandindo

0.75

 للمعارف

0.74

zerland

0.71

aarrggbb

0.70

 JpaRepository

0.69

MessageTagHelper

0.67

Демографія

0.65

Activations Density 5.070%

C++ code snippets and file paths

Non-English words

No Comments

No Known Activations