INDEX

Explanations

words relating to atomization or scientific measurement

oai_token-act-pair · gemini-2.0-flash

izing

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

ChildIndex

-0.48

маш

-0.44

 Flooring

-0.44

ut

-0.43

احبه

-0.43

 eller

-0.43

urlpatterns

-0.42

or

-0.42

chir

-0.42

“

-0.42

POSITIVE LOGITS

 kasarigan

1.04

 itſelf

0.89

 EconPapers

0.82

Datuak

0.81

^(@)

0.79

 myſelf

0.78

 المعيارى

0.78

RenderAtEndOf

0.78

 pleaſure

0.77

 syringe

0.76

Activations Density 1.379%

words relating to atomization or scientific measurement

izing

No Comments

No Known Activations