INDEX

Explanations

medical and biological terminology

oai_token-act-pair · gemini-2.0-flash

Medical and throat issues

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ак

-0.43

 scom

-0.43

デューサー

-0.42

 Leip

-0.42

poietic

-0.41

 createState

-0.40

Diwedd

-0.40

legt

-0.39

getc

-0.39

Inhalt

-0.38

POSITIVE LOGITS

 tons

0.84

abestanden

0.79

Tons

0.77

Personendaten

0.74

tons

0.74

+#+#

0.73

 Tons

0.73

 esternos

0.72

 ویکی‌پدی

0.69

sizeCache

0.69

Activations Density 1.181%

medical and biological terminology

Medical and throat issues

No Comments

No Known Activations