INDEX

Explanations

phrases or questions that display consideration, contemplation, doubt or uncertainty.

oai_token-act-pair · gemini-2.0-flash

what

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

AttributeSet

-0.68

Abitanti

-0.67

出版年

-0.65

IUrlHelper

-0.62

 '\\;'

-0.51

buttonBar

-0.51

TagMode

-0.51

alnız

-0.50

érons

-0.50

ScopeManager

-0.50

POSITIVE LOGITS

 what

2.19

what

1.97

What

1.83

 What

1.80

 WHAT

1.57

WHAT

1.48

whats

1.28

 whats

1.20

 hvad

1.13

hva

1.13

Activations Density 0.892%

phrases or questions that display consideration, contemplation, doubt or uncertainty.

what

No Comments

No Known Activations