INDEX

Explanations

words or abbreviations related to technology and electronics

oai_token-act-pair · gemini-2.0-flash

include

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

下载附件

-0.87

]")]

-0.72

StoryboardSegue

-0.71

__":

-0.70

 <=",

-0.65

 defaultstate

-0.64

Hozzáférés

-0.63

וויק

-0.63

atguigu

-0.63

AndEndTag

-0.62

POSITIVE LOGITS

 included

1.22

 Included

1.19

included

1.04

 INCLUDED

1.01

Included

1.00

Include

0.87

 include

0.85

 INCLUDE

0.83

 Include

0.83

 inclusion

0.82

Activations Density 2.302%

words or abbreviations related to technology and electronics

include

No Comments

No Known Activations