INDEX

Explanations

medical studies

oai_token-act-pair · gemini-2.0-flash

Numbers

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kasarigan

-0.65

 CreateTagHelper

-0.62

 ***!

-0.60

KEYCODE

-0.58

 חיצוניים

-0.57

ритори

-0.56

Хьажоргаш

-0.56

ceğiniz

-0.55

OGND

-0.55

 protoimpl

-0.55

POSITIVE LOGITS

 epist

0.46

Tower

0.46

 corrid

0.46

/**

0.45

 firebaseConfig

0.45

[.

0.44

 decimals

0.43

 کش

0.43

 Spur

0.42

机

0.42

Activations Density 2.958%

medical studies

Numbers

No Comments

No Known Activations