INDEX

Explanations

phrases containing "to," often followed by a verb or a word suggesting action or purpose.

oai_token-act-pair · gemini-2.0-flash

to

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

 مشين

-0.83

IsMutable

-0.82

 ExecuteAsync

-0.73

SequentialGroup

-0.68

 betweenstory

-0.68

EndGlobalSection

-0.67

 سكانية

-0.64

 onCreateView

-0.64

 ModelExpression

-0.64

Referencie

-0.63

POSITIVE LOGITS

ouille

0.50

 fonds

0.49

cshtml

0.49

brtc

0.49

lifecycle

0.47

 isEnabled

0.47

 miss

0.46

chkin

0.46

assembler

0.45

 using

0.44

Activations Density 6.502%

phrases containing "to," often followed by a verb or a word suggesting action or purpose.

to

No Comments

No Known Activations