© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28775
    Prev
    Next
    INDEX
    Explanations

    crossroads and intersection

    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_10_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
    IS
    0.74
    {
    0.66
    다
    0.60
    ف
    0.58
    )
    0.57
     Monate
    0.56
    O
    0.56
    োপ
    0.56
    潺
    0.56
     Muskel
    0.55
    POSITIVE LOGITS
    ed
    0.66
    ем
    0.65
     나서
    0.65
    hary
    0.63
     بیاکت
    0.63
    s
    0.62
     ነ
    0.62
     útiles
    0.62
     იყ
    0.61
    of
    0.61
    Activations Density 0.010%

    No Known Activations