INDEX

Explanations

words that provide context to topics with multiple perspectives

oai_token-act-pair · gemini-2.0-flash

breast cancer

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

haped

-0.56

typeparam

-0.56

izing

-0.56

pecific

-0.56

vē

-0.56

gehalt

-0.55

upported

-0.53

IUrlHelper

-0.52

초

-0.52

pensive

-0.50

POSITIVE LOGITS

 surla

0.65

line

0.64

 Савезне

0.63

sizeCache

0.60

دانشنامهٔ

0.60

lines

0.59

lineTo

0.57

kháu

0.56

esez

0.56

цездатний

0.56

Activations Density 3.245%

words that provide context to topics with multiple perspectives

breast cancer

No Comments

No Known Activations