INDEX

Explanations

words related to fictional media like video games and shows, often with many numbers surrounding the activation

oai_token-act-pair · gemini-2.0-flash

Kyuranger

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

ScopeManager

-0.63

EndInit

-0.54

CodedInputStream

-0.54

 defaultstate

-0.53

сылкі

-0.49

ifndef

-0.49

layoutControl

-0.48

 MatDialog

-0.48

mybatisplus

-0.46

 autorytatywna

-0.46

POSITIVE LOGITS

 Italijanski

0.63

Distribuzione

0.58

GOTREF

0.57

ザード

0.57

եկ

0.55

victim

0.53

 redé

0.53

 Detalles

0.52

CURLOPT

0.52

runOnUiThread

0.52

Activations Density 4.271%

words related to fictional media like video games and shows, often with many numbers surrounding the activation

Kyuranger

No Comments

No Known Activations