INDEX

Explanations

words and numbers found in scientific studies describing patients and data collection

oai_token-act-pair · gemini-2.0-flash

study participants

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

脚注の使い方

-0.92

 snippetHide

-0.85

ieteur

-0.77

enumi

-0.70

 chré

-0.69

tagHelperRunner

-0.69

 étrangères

-0.69

 MainAxisSize

-0.69

tvguidetime

-0.69

 démocr

-0.68

POSITIVE LOGITS

 subjects

0.56

 subject

0.46

 well

0.45

 adults

0.44

gy

0.42

Subjects

0.42

struts

0.40

 adult

0.40

 volunteers

0.40

karta

0.40

Activations Density 7.625%

words and numbers found in scientific studies describing patients and data collection

study participants

No Comments

No Known Activations