© 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. 45429
    Prev
    Next
    INDEX
    Explanations

    SDXC card, PAGE gel

    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
    你
    0.73
    st
    0.73
     synthes
    0.64
    last
    0.62
    lation
    0.61
    synt
    0.61
    erial
    0.60
    ilation
    0.58
    mall
    0.58
    spend
    0.58
    POSITIVE LOGITS
    ן
    0.88
    ي
    0.85
    ق
    0.79
    ERSON
    0.72
    ع
    0.67
    ur
    0.66
    dır
    0.66
    ORITY
    0.66
     honti
    0.63
    EAR
    0.62
    Activations Density 0.001%

    No Known Activations