INDEX

Explanations

text appearing in legal or scientific citations

oai_token-act-pair · gemini-2.0-flash

Academic documents

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

thage

-0.57

toContain

-0.54

 anunci

-0.45

ETHING

-0.44

cu

-0.44

SPARENT

-0.43

rscheinlich

-0.43

 ostavi

-0.41

arach

-0.41

ieste

-0.41

POSITIVE LOGITS

 Cæsar

0.68

 Ambas

0.66

rungsseite

0.66

 OnInit

0.66

 MessageBoxIcon

0.64

 Jefus

0.63

 Diſ

0.60

 Rosalind

0.60

 dieß

0.60

WebControls

0.59

Activations Density 1.102%

text appearing in legal or scientific citations

Academic documents

No Comments

No Known Activations

text appearing in legal or scientific citations

Academic documents

No Comments

No Known Activations