© 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. 34567
    Prev
    Next
    INDEX
    Explanations

    greek letters and symbols

    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
    entwicklung
    0.69
    -
    0.68
     beta
    0.67
    にか
    0.65
    ta
    0.64
     in
    0.61
    “
    0.60
    ও
    0.60
    ючи
    0.59
    ೆ
    0.58
    POSITIVE LOGITS
     integrantes
    0.81
    হ
    0.78
    ک
    0.77
     accion
    0.72
     faites
    0.71
     eind
    0.69
    ক
    0.69
     имеются
    0.68
     principales
    0.66
    ifiques
    0.66
    Activations Density 0.001%

    No Known Activations