INDEX

Explanations

citations to scientific papers in the format "Author et al."

oai_token-act-pair · gemini-2.0-flash

[author] et al

np_token-act-pair-logits · gemini-2.0-flash

et

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

load

-0.50

ViewById

-0.48

ViewFeatures

-0.45

 load

-0.43

avimas

-0.41

šené

-0.41

jni

-0.41

 jsPsych

-0.40

TagHelper

-0.40

ay

-0.40

POSITIVE LOGITS

et

0.93

 فريبيس

0.82

 AppCompatTheme

0.73

 صوتيه

0.69

tagHelperRunner

0.68

 ISNI

0.67

 TextAppearance

0.63

httphttps

0.62

GEBURTSDATUM

0.61

afficheront

0.60

Activations Density 1.429%

citations to scientific papers in the format "Author et al."

[author] et al

et

No Comments

No Known Activations