© 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. 86643
    Prev
    Next
    INDEX
    Explanations

    pecan, pie, butter, peanut

    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
    ب
    0.73
     argentina
    0.68
     spinel
    0.66
     buty
    0.66
    im
    0.66
     ordinateur
    0.66
    鹖
    0.66
     Acacia
    0.64
     pyrid
    0.64
     sistem
    0.63
    POSITIVE LOGITS
    ן
    1.13
    _
    0.88
    та
    0.77
    る
    0.73
    ية
    0.70
    า
    0.66
    ا
    0.62
     në
    0.61
    ্স
    0.60
    の見
    0.59
    Activations Density 0.001%

    No Known Activations