INDEX

Explanations

phrases expressing surprise or incredulity

oai_token-act-pair · gemini-2.0-flash

imagine

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

########.

-0.96

 MainAxisSize

-0.76

 виправивши

-0.71

 CURIAM

-0.70

aarrggbb

-0.68

rungsseite

-0.65

 Савезне

-0.65

 كومونز

-0.64

 StatelessWidget

-0.62

 AssemblyTitle

-0.62

POSITIVE LOGITS

RetentionPolicy

0.40

 Semoga

0.38

IBOutlet

0.38

pectiva

0.37

 azon

0.36

мети

0.35

nvarchar

0.34

 slightly

0.34

Hope

0.34

ISH

0.34

Activations Density 2.544%

phrases expressing surprise or incredulity

imagine

No Comments

No Known Activations