INDEX

Explanations

code-related keywords and identifiers, especially related to hardware interfaces or system calls

oai_token-act-pair · gemini-2.0-flash

Code and system configuration

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

 VIAF

-0.50

findpost

-0.46

VIAF

-0.43

he

-0.41

mappedBy

-0.40

 المعيارى

-0.40

utal

-0.40

 arşivlendi

-0.39

min

-0.39

sum

-0.38

POSITIVE LOGITS

 myſelf

0.79

 Reſ

0.72

 Majefty

0.70

 Houſe

0.69

 itſelf

0.69

 Anſ

0.68

 themſelves

0.68

 Moslem

0.67

]--;

0.66

 Theſe

0.66

Activations Density 6.619%

code-related keywords and identifiers, especially related to hardware interfaces or system calls

Code and system configuration

No Comments

No Known Activations