INDEX

Explanations

references to Microsoft Office file formats

oai_token-act-pair · gemini-2.0-flash

Office documents

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 HasFactory

-0.60

 SafeMath

-0.59

 تضيفلها

-0.57

شهاد

-0.52

getMinutes

-0.52

 szóci

-0.49

 spleen

-0.49

findpost

-0.47

setBold

-0.47

mybatisplus

-0.46

POSITIVE LOGITS

لينكات

0.62

 للاسماء

0.62

AxisAlignment

0.62

UnknownFieldSet

0.59

 MonoBehaviour

0.56

 للمعارف

0.54

SerializedSize

0.54

PRNewswire

0.52

Programmer

0.49

harusnya

0.49

Activations Density 8.396%

references to Microsoft Office file formats

Office documents

No Comments

No Known Activations