INDEX

Explanations

equations and mathematical notation

oai_token-act-pair · gemini-2.0-flash

numbers

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

rachtet

-0.55

arakhand

-0.52

WithIOException

-0.51

 photographie

-0.50

PRNewswire

-0.50

énage

-0.50

yaratan

-0.50

titleMargin

-0.49

phosa

-0.49

ghế

-0.48

POSITIVE LOGITS

şiv

0.62

Välislingid

0.56

Espèce

0.54

ContentAlignment

0.50

片

0.50

oa̍t

0.49

kháu

0.49

 ImportError

0.49

bildung

0.48

DebuggerStep

0.48

Activations Density 2.286%

equations and mathematical notation

numbers

No Comments

No Known Activations