© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66185
    Prev
    Next
    INDEX
    Explanations

    imprinting, imide, duplications

    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_41_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
     ball
    0.69
    Ball
    0.69
     Ball
    0.61
    球
    0.61
    ball
    0.58
     BALL
    0.58
    ボール
    0.57
     الكرة
    0.55
     stick
    0.54
     球
    0.50
    POSITIVE LOGITS
     im
    0.68
    imide
    0.54
     им
    0.50
    UPD
    0.48
     imprinted
    0.46
     imprint
    0.45
     unip
    0.45
     dup
    0.42
    ulkner
    0.41
     Im
    0.40
    Activations Density 0.013%

    No Known Activations