INDEX

Explanations

parts of research papers related to the immune system.

oai_token-act-pair · gemini-2.0-flash

immunology

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 BorderRadius

-0.83

 InputDecoration

-0.79

 ProtoMessage

-0.77

DockStyle

-0.75

المناصب

-0.72

 surla

-0.72

contentLoaded

-0.68

MessageTagHelper

-0.66

SBATCH

-0.65

 Италијани

-0.64

POSITIVE LOGITS

omeric

0.45

*************/

0.42

::_('

0.41

protein

0.41

 appareil

0.40

 ви

0.40

 deput

0.39

lic

0.39

cleros

0.38

 impost

0.38

Activations Density 8.110%

parts of research papers related to the immune system.

immunology

No Comments

No Known Activations