INDEX

Explanations

various unusual non-alphabetical characters and character clusters, as well as smiling

oai_token-act-pair · gemini-2.0-flash

non-English fragments

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

RegressionTest

-0.80

]='\

-0.71

MLLoader

-0.71

GEBURTSDATUM

-0.70

 Wicidata

-0.69

 الاطلاع

-0.69

脚注の使い方

-0.68

 fallu

-0.66

 تضيفلها

-0.64

 Hift

-0.63

POSITIVE LOGITS

ρης

0.40

 forma

0.39

 нему

0.38

 него

0.38

“

0.37

ud

0.36

 eben

0.36

աբ

0.36

 ему

0.36

提

0.36

Activations Density 0.067%

various unusual non-alphabetical characters and character clusters, as well as smiling

non-English fragments

No Comments

No Known Activations