© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 16363
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     headroom
    0.80
     prosperity
    0.77
     suitors
    0.73
     sunshine
    0.71
     correspondingly
    0.70
     ዋ
    0.70
     tonnage
    0.69
    ات
    0.68
     perishable
    0.68
    ска
    0.67
    POSITIVE LOGITS
     uvijek
    0.84
     Спасибо
    0.81
    Danke
    0.79
    CMS
    0.77
     Ст
    0.73
    ampa
    0.73
    orky
    0.72
    怜
    0.72
     Danke
    0.71
     Produits
    0.71
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.