INDEX

Explanations

words or phrases suggesting something residual or remaining

oai_token-act-pair · gemini-2.0-flash

remnants, leftovers

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

Negative Logits

 StatefulWidget

-0.68

NavController

-0.58

:✨

-0.58

RegistryLite

-0.55

Biografie

-0.55

aarrggbb

-0.54

#+#

-0.53

openzeppelin

-0.53

Ngb

-0.52

 StatelessWidget

-0.52

POSITIVE LOGITS

 urmă

0.60

AutoScaleMode

0.57

old

0.56

 antigas

0.54

 outdated

0.54

fxml

0.54

addContainerGap

0.54

 retro

0.52

 antiguas

0.52

 antiguo

0.51

Activations Density 2.126%

words or phrases suggesting something residual or remaining

remnants, leftovers

No Known Activations