INDEX

Explanations

articles "the" followed by words related to industrialization, and some historic events

oai_token-act-pair · gemini-2.0-flash

the

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 виправивши

-0.75

 فريبيس

-0.72

///</

-0.72

脚注の使い方

-0.67

}>;

-0.66

évaluateur

-0.66

southern

-0.65

AutoScaleMode

-0.65

 northern

-0.65

IntoConstraints

-0.63

POSITIVE LOGITS

 West

2.36

West

2.11

 WEST

1.90

 west

1.71

WEST

1.67

west

1.59

 East

1.45

East

1.30

 east

1.14

 EAST

1.10

Activations Density 2.670%

articles "the" followed by words related to industrialization, and some historic events

the

No Comments

No Known Activations