INDEX

Explanations

words that look like usernames and filenames

oai_token-act-pair · gemini-2.0-flash

nom

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

AsUp

-0.84

expandindo

-0.84

 Majefty

-0.83

 Anſ

-0.83

Efq

-0.82

 IBRARY

-0.82

 BorderSide

-0.81

 AppColors

-0.78

 Theſe

-0.77

ruptedException

-0.77

POSITIVE LOGITS

 name

1.50

name

1.30

 names

1.27

 Name

1.21

Name

1.21

NAME

0.98

names

0.97

 Names

0.96

 NAME

0.96

Names

0.91

Activations Density 1.483%

words that look like usernames and filenames

nom

No Comments

No Known Activations