INDEX

Explanations

words related to official procedures involving government agencies

oai_token-act-pair · gemini-2.0-flash

News articles

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

OGND

-0.79

 estekak

-0.71

Демографія

-0.66

elemField

-0.62

ंदीखरीदारी

-0.59

 препратки

-0.59

[*]

-0.57

 himo

-0.56

 bezeichneter

-0.55

 المعرف

-0.54

POSITIVE LOGITS

New

0.58

New

0.53

SpringBoot

0.53

 AssemblyCulture

0.50

MAO

0.47

لينكات

0.46

ChildScrollView

0.45

 disponibilités

0.45

OnAdd

0.45

 uska

0.44

Activations Density 5.977%

words related to official procedures involving government agencies

News articles

No Comments

No Known Activations