INDEX

Explanations

sequences of characters like in a URL and also sentences about the politics of Israel

oai_token-act-pair · gemini-2.0-flash

recognition

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

 resourceCulture

-0.95

IntoConstraints

-0.79

зулта

-0.77

 '\\;'

-0.73

 fieldNum

-0.72

 فريبيس

-0.71

 "..\..\..\

-0.69



-0.67

AsUp

-0.67

 <>",

-0.65

POSITIVE LOGITS

 recognition

1.70

 Recognition

1.48

 recognize

1.46

 recognized

1.46

Recognition

1.44

 RECOGN

1.40

 recognizing

1.35

recognition

1.35

 recognizes

1.32

recognized

1.29

Activations Density 0.810%

sequences of characters like in a URL and also sentences about the politics of Israel

recognition

No Comments

No Known Activations