© 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. 11217
    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
    ESTIC
    0.73
    解答
    0.69
    рис
    0.69
     columnIndex
    0.69
    ק
    0.67
    分類
    0.67
    全身
    0.66
    PosX
    0.66
    놈
    0.66
    被迫
    0.65
    POSITIVE LOGITS
    an
    0.91
    elun
    0.85
     Jody
    0.84
    opening
    0.81
     hinzuf
    0.80
    anay
    0.79
    embedded
    0.77
    able
    0.77
    le
    0.77
    hazard
    0.76
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.