INDEX

Explanations

the names of schools or places related to schools or education

oai_token-act-pair · gemini-2.0-flash

mentions of California

np_token-act-pair-logits · gpt-4o-mini

California

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aarrggbb

-0.67

IntoConstraints

-0.66

 يتيمه

-0.65

Искәрмәләр

-0.64

Hozzáférés

-0.63

Дереккөздер

-0.59

EOT

-0.58

Vidite

-0.58

Efq

-0.57

httphttps

-0.57

POSITIVE LOGITS

 California

0.99

Los

0.91

 CALIFORNIA

0.91

California

0.89

 Calif

0.85

CALIFORNIA

0.85

Los

0.80

 californ

0.75

Calif

0.75

 Californie

0.75

Activations Density 2.133%

the names of schools or places related to schools or education

mentions of California

California

No Comments

No Known Activations