INDEX

Explanations

auxiliary verb "have" and forms of "be".

oai_token-act-pair · gemini-2.0-flash

have

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

 NSCoder

-0.50

디오

-0.49

 juges

-0.49

 toalha

-0.48

mädchen

-0.48

 actifs

-0.48

thétique

-0.47

 esetben

-0.47

 anhänger

-0.47

Likes

-0.47

POSITIVE LOGITS

RenderAtEndOf

0.74

WebVitals

0.70

存于互联网档案馆

0.69

StructEnd

0.67

DeleteBehavior

0.65

 useRouter

0.64

AndEndTag

0.64

 مشين

0.60

 OFDb

0.60

PhysRevLett

0.59

Activations Density 1.201%

auxiliary verb "have" and forms of "be".

have

No Comments

No Known Activations