© 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. 38780
    Prev
    Next
    INDEX
    Explanations

    mind flayer, eating, muscle connection, MindScope

    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
    ;
    0.71
     an
    0.69
    দ
    0.67
     avant
    0.66
     lequel
    0.65
     DISTINCT
    0.65
     strides
    0.65
    oł
    0.65
     enabled
    0.64
     arguments
    0.64
    POSITIVE LOGITS
    1
    0.73
    ice
    0.70
    irc
    0.69
    underscore
    0.65
    к
    0.64
    ếu
    0.63
    irt
    0.63
    ifornia
    0.62
    ip
    0.61
    IEC
    0.61
    Activations Density 0.014%

    No Known Activations