INDEX

Explanations

academic writing related to studies, including researchers, and students.

oai_token-act-pair · gemini-2.0-flash

student

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 former

-0.63

Former

-0.60

 مُعرِّف

-0.58

 Mommy

-0.57

 mother

-0.57

 Former

-0.56

 كومونز

-0.54

 Monfieur

-0.54

 mantan

-0.54

יצוני

-0.53

POSITIVE LOGITS

 student

0.78

 <<<<<<<<<<<<<<

0.71

 students

0.71

MigrationBuilder

0.68

 undergraduate

0.67

 mahasiswa

0.65

 Studenten

0.63

 Student

0.63

 autorytatywna

0.60

nologie

0.59

Activations Density 1.648%

academic writing related to studies, including researchers, and students.

student

No Comments

No Known Activations