INDEX

Explanations

strings of characters such as numbers and special characters, often found in metadata, and also finds words associated with research article abstracts.

oai_token-act-pair · gemini-2.0-flash

absence

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

TagHelper

-0.60

ंदीखरीदारी

-0.59

BeginContext

-0.57

XmlAccessType

-0.56

rungsseite

-0.55

addGap

-0.53

 pinulongan

-0.51

TagMode

-0.51

oa̍t

-0.50

astet

-0.49

POSITIVE LOGITS

 absence

1.23

无

1.18

 Aucune

1.18

 unavailable

1.15

 absent

1.13

non

1.13

 Aucun

1.13

無

1.13

Aucun

1.12

no

1.09

Activations Density 33.806%

strings of characters such as numbers and special characters, often found in metadata, and also finds words associated with research article abstracts.

absence

No Comments

No Known Activations

strings of characters such as numbers and special characters, often found in metadata, and also finds words associated with research article abstracts.

absence

No Comments

No Known Activations