INDEX

Explanations

words related to education, faith, and relationships

oai_token-act-pair · gemini-2.0-flash

class/course

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 חיצוניים

-0.50

nasse

-0.42

 siff

-0.41

みな

-0.41

 kasarigan

-0.40

Sire

-0.40

SharedCtor

-0.40

IUrlHelper

-0.40

TestClass

-0.40

 PyQt

-0.40

POSITIVE LOGITS

 CreateTagHelper

0.71

findpost

0.69

Vidite

0.65

 يتيمه

0.65

 mouseY

0.65

phorus

0.63

ulemon

0.61

interopRequire

0.61

émoc

0.61

windowFixed

0.60

Activations Density 16.710%

words related to education, faith, and relationships

class/course

No Comments

No Known Activations