INDEX

Explanations

general language that is often used when describing or reviewing video games

oai_token-act-pair · gemini-2.0-flash

video games

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

 Players

-0.79

 players

-0.77

 Games

-0.72

 games

-0.67

 GAME

-0.66

 Game

-0.66

 Mechanics

-0.65

 게임

-0.65

Players

-0.64

Games

-0.63

POSITIVE LOGITS

LabelTagHelper

0.80

migrationBuilder

0.74

RTDA

0.66

tvguidetime

0.65

WebServlet

0.59

exitRule

0.59

GraphicsUnit

0.58

 virtuel

0.57

bufio

0.57

TestingModule

0.56

Activations Density 2.625%

general language that is often used when describing or reviewing video games

video games

No Comments

No Known Activations