© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91804
    Prev
    Next
    INDEX
    Explanations

    Robin + surname

    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
     könnte
    0.64
     deberá
    0.64
    (
    0.63
     considere
    0.62
     što
    0.61
     großen
    0.61
     cree
    0.61
    île
    0.61
     weil
    0.61
    .
    0.61
    POSITIVE LOGITS
    ق
    0.92
    ن
    0.90
    n
    0.88
    p
    0.86
    nX
    0.83
    h
    0.78
    ต
    0.75
    nq
    0.75
    ح
    0.72
    ٹ
    0.71
    Activations Density 0.000%

    No Known Activations