© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8554
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Oceania
    0.90
    례
    0.82
     LMFBR
    0.81
     Faroe
    0.80
     pheasant
    0.80
     Barbados
    0.80
    OT
    0.79
    NSY
    0.79
     OCPP
    0.79
     Бар
    0.78
    POSITIVE LOGITS
    علی
    0.68
    erdings
    0.67
    ا
    0.67
    مكان
    0.67
    情况下
    0.66
    erweise
    0.64
     slowing
    0.63
    lığ
    0.63
    很少
    0.63
    maker
    0.63
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.