© 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. 121735
    Prev
    Next
    INDEX
    Explanations

    from now on

    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
    I
    0.76
    ו
    0.64
    같이
    0.60
    r
    0.59
    ر
    0.57
    妸
    0.57
    September
    0.56
    bbene
    0.55
    ubuk
    0.54
    o
    0.54
    POSITIVE LOGITS
     to
    0.68
     are
    0.66
    RO
    0.66
    ₕ
    0.62
     publicités
    0.58
    <0x0D>
    0.55
    ści
    0.55
    ৭
    0.55
    ICK
    0.54
     votes
    0.54
    Activations Density 0.003%

    No Known Activations