INDEX

Explanations

words expressing uncertainty or problems, particularly in technical discussions

oai_token-act-pair · gemini-2.0-flash

missing, improvements, helpful

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

enumii

-0.72

nestjs

-0.65

Hentet

-0.64

曖昧さ回避

-0.60

homonymie

-0.60

rairie

-0.60

 المعيارى

-0.60

 disambiguazione

-0.59

IntoConstraints

-0.58

ContentAsync

-0.57

POSITIVE LOGITS

 here

2.95

 aquí

2.25

here

2.23

Here

2.16

 Here

2.13

 здесь

2.09

 aici

2.03

ici

1.99

 aqui

1.99

 HERE

1.96

Activations Density 2.563%

words expressing uncertainty or problems, particularly in technical discussions

missing, improvements, helpful

No Comments

No Known Activations

words expressing uncertainty or problems, particularly in technical discussions

missing, improvements, helpful

No Comments

No Known Activations