INDEX

Explanations

mixed alphanumeric and special characters, possible code

oai_token-act-pair · gemini-2.0-flash

computer code and math notation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 مشين

-0.77

audiovisuel

-0.72

 Tacitus

-0.70

 rhinoceros

-0.69

 princesse

-0.69

 Calhoun

-0.68

 Remus

-0.68

Vidite

-0.68

 ostavi

-0.67

 ProtoMessage

-0.67

POSITIVE LOGITS

zki

0.50

 Kirby

0.47

PURE

0.47

Kirby

0.47

ftr

0.44

dla

0.44

 gens

0.44

Pure

0.43

hla

0.43

eaway

0.43

Activations Density 5.101%

mixed alphanumeric and special characters, possible code

computer code and math notation

No Comments

No Known Activations