© 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. 226068
    Prev
    Next
    INDEX
    Explanations

    tremendous amount of

    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
    ak
    0.77
    i
    0.75
    on
    0.75
    im
    0.71
    kill
    0.69
    er
    0.69
    n
    0.68
    ul
    0.67
    ments
    0.67
    velocity
    0.66
    POSITIVE LOGITS
     for
    0.77
     et
    0.73
    ش
    0.68
     as
    0.67
     curators
    0.66
     el
    0.64
     us
    0.64
     oaks
    0.64
     franca
    0.64
    س
    0.64
    Activations Density 0.000%

    No Known Activations