INDEX

Explanations

a mix of web button HTML code and words relating to medical imaging technology

oai_token-act-pair · gemini-2.0-flash

medical scans

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

 ―――――

-1.02

ThroughAttribute

-1.01

RetentionPolicy

-1.00

ImageContext

-0.99

 myſelf

-0.98

^(@)

-0.98

 itſelf

-0.95

<?

-0.95

EndInit

-0.95

tagHelperRunner

-0.95

POSITIVE LOGITS

0.51

0.50

↵

0.47

ssa

0.46

0.44

ss

0.44

</b>

0.43

radio

0.41

Activations Density 1.033%

a mix of web button HTML code and words relating to medical imaging technology

medical scans

No Comments

No Known Activations