INDEX

Explanations

terminology related to medical conditions and anatomy

oai_token-act-pair · gemini-2.0-flash

biological and medical research

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

 RESISTANCE

-0.59

 capes

-0.59

Efq

-0.54

inerja

-0.54

ształ

-0.54

enumi

-0.52

 Theſe

-0.51

 acorns

-0.50

ifflin

-0.50

niosek

-0.50

POSITIVE LOGITS

 оригіналу

0.58

 lenker

0.54

 للاسماء

0.52

тистика

0.47

ข้าง

0.45

Hej

0.45

blon

0.44

 particularmente

0.43

رشف

0.43

amerikanischer

0.43

Activations Density 1.086%

terminology related to medical conditions and anatomy

biological and medical research

No Comments

No Known Activations