© 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. 90797
    Prev
    Next
    INDEX
    Explanations

    Fleetwood Mac

    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
    ของ
    0.79
    س
    0.74
    า
    0.73
    ل
    0.70
     of
    0.69
    های
    0.67
    ใส
    0.64
     are
    0.64
    د
    0.64
    ä
    0.63
    POSITIVE LOGITS
     বাস্তবিক
    0.61
    ༦
    0.61
    ᱘
    0.59
    t
    0.56
    (“
    0.55
    tio
    0.55
     самое
    0.55
     (^{
    0.55
    ኛው
    0.54
     нашли
    0.54
    Activations Density 0.000%

    No Known Activations