© 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. 90833
    Prev
    Next
    INDEX
    Explanations

    shadow, QA, ahaha

    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
    ม
    0.77
    not
    0.73
    ad
    0.71
    is
    0.70
    وما
    0.67
    نا
    0.65
    나
    0.64
    isering
    0.63
    م
    0.63
    s
    0.62
    POSITIVE LOGITS
    لی
    0.66
    RACT
    0.64
    eri
    0.64
    IN
    0.61
    ка
    0.61
     are
    0.61
    zeit
    0.60
    rix
    0.59
    া
    0.59
    CE
    0.59
    Activations Density 0.000%

    No Known Activations