INDEX

Explanations

words related to medical conditions, particularly tumors and wounds, and related procedures

oai_token-act-pair · gemini-2.0-flash

medical issues

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pru

-0.54

ORTE

-0.50

útil

-0.50

 reverse

-0.49

<bos>

-0.48

 Systematic

-0.48

cardo

-0.47

Ancien

-0.46

vog

-0.46

POSITIVE LOGITS

 оригіналу

0.85

EDEFAULT

0.76

 disambiguazione

0.76

WebVitals

0.75

contentLoaded

0.74

 contextLoads

0.69

+#+#

0.69

blurRadius

0.69

 habet

0.68

ApiProperty

0.68

Activations Density 3.884%

words related to medical conditions, particularly tumors and wounds, and related procedures

medical issues

No Comments

No Known Activations