INDEX

Explanations

code snippets related to login procedures or campaigns

oai_token-act-pair · gemini-2.0-flash

login

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

rungsseite

-0.86

 مرئيه

-0.79

 estekak

-0.72

AddTagHelper

-0.71

Manbalar

-0.70

 BoxDecoration

-0.70

principalColumn

-0.67

 متعلقه

-0.65

 autorytatywna

-0.64

ритори

-0.64

POSITIVE LOGITS

 form

0.63

0.56

form

0.56

 Form

0.54

 FORM

0.47

 forms

0.47

 Sistem

0.45

ся

0.43

forms

0.43

 Forms

0.43

Activations Density 1.560%

code snippets related to login procedures or campaigns

login

No Comments

No Known Activations