INDEX

Explanations

words that might be found in online forum posts, especially those about technical, legal, or fictional topics.

oai_token-act-pair · gemini-2.0-flash

Mira

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

#!/

-0.42

سجيل

-0.40

Highly

-0.39

…

-0.34

 Highly

-0.34

 package

-0.33

 Créez

-0.33

друг

-0.33

 nocturno

-0.33

couvrir

-0.32

POSITIVE LOGITS

SourceChecksum

0.89

 jScrollPane

0.76

InteropServices

0.75

 initComponents

0.73

 ProtoMessage

0.71

 дописавши

0.69

MessageOf

0.69

Personendaten

0.68

 صوتيه

0.66

ьаж

0.65

Activations Density 4.791%

words that might be found in online forum posts, especially those about technical, legal, or fictional topics.

Mira

No Comments

No Known Activations