INDEX

Explanations

terms related to wireless communication technology

oai_token-act-pair · gemini-2.0-flash

network, communication

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

#+#

-1.10

+#+#

-0.93

 uſe

-0.90

 houſe

-0.88

Efq

-0.87

 Jefus

-0.86

 myſelf

-0.85

 ſtate

-0.84

 itſelf

-0.83

 Económica

-0.81

POSITIVE LOGITS

 para

0.43

bar

0.42

 пор

0.42

듯

0.42

createServer

0.41

แต

0.41

 Micro

0.40

bo

0.40

IE

0.40

Activations Density 21.136%

terms related to wireless communication technology

network, communication

No Comments

No Known Activations