INDEX

Explanations

the word "order" followed by "to"

oai_token-act-pair · gemini-2.0-flash

order

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 order

-2.05

 Order

-1.72

order

-1.66

Order

-1.59

 ORDER

-1.48

 orders

-1.27

ORDER

-1.23

 ordre

-1.20

 ordine

-1.17

 ordem

-1.11

POSITIVE LOGITS

 snippetHide

0.93

 AssemblyTitle

0.89

цездатний

0.88

 Roskov

0.88

featureID

0.87

WebElementEntity

0.87

 BorderRadius

0.79

HtmlAttribute

0.78

MessageTagHelper

0.77

 الرخصة

0.77

Activations Density 4.813%

the word "order" followed by "to"

order

No Comments

No Known Activations