INDEX

Explanations

language related to biological studies and medical treatments

oai_token-act-pair · gemini-2.0-flash

scientific research

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WebElementEntity

-0.66

 Infórmanos

-0.66

 disambiguazione

-0.65

 صوتيه

-0.63

CrossRef

-0.63

 дописавши

-0.62

 الرياضيه

-0.61

 Мексичка

-0.61

 '\\;'

-0.60

Identyfik

-0.60

POSITIVE LOGITS

 live

0.78

 Live

0.63

live

0.60

LIVE

0.57

Live

0.56

 kasarigan

0.53

ื่อ

0.53

 LIVE

0.52

 suicide

0.51

suicide

0.48

Activations Density 2.411%

language related to biological studies and medical treatments

scientific research

No Comments

No Known Activations