© 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. 122721
    Prev
    Next
    INDEX
    Explanations

    chamartín, charlottetown, provincetown

    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
    لي
    0.79
    t
    0.75
    ي
    0.74
    ONG
    0.71
     pueden
    0.70
     ожида
    0.67
     cambió
    0.67
    ༦
    0.67
     proiect
    0.66
    ৬
    0.66
    POSITIVE LOGITS
    ;
    0.84
    al
    0.76
    O
    0.76
    as
    0.73
    ar
    0.70
    eat
    0.70
    T
    0.70
    er
    0.69
    il
    0.68
    acquired
    0.66
    Activations Density 0.005%

    No Known Activations