© 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. 35030
    Prev
    Next
    INDEX
    Explanations

    byte array or typed array data

    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
    ل
    0.96
    ל
    0.89
    in
    0.76
    ትር
    0.76
    تش
    0.73
    اب
    0.72
    mse
    0.70
    myd
    0.70
    infs
    0.70
    Admin
    0.68
    POSITIVE LOGITS
    не
    0.71
    ü
    0.64
     đầy
    0.61
     đều
    0.58
    ۔
    0.58
     breathed
    0.56
    는
    0.55
    ள்
    0.54
     milestone
    0.54
     przer
    0.54
    Activations Density 0.001%

    No Known Activations