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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34300
    Prev
    Next
    INDEX
    Explanations

    mar, mer, ang, om

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    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
    ил
    0.82
    ли
    0.81
    g
    0.77
    ח
    0.71
     I
    0.70
    ü
    0.70
    скую
    0.68
    ة
    0.68
    ط
    0.67
    с
    0.67
    POSITIVE LOGITS
    the
    0.83
    <0x0D>
    0.68
    are
    0.61
    </h3>
    0.60
     কহ
    0.59
     وړیا
    0.58
    ियार
    0.58
    ੍ਰ
    0.55
     Empres
    0.54
     señalado
    0.54
    Activations Density 0.002%

    No Known Activations