© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 108057
    Prev
    Next
    INDEX
    Explanations

    CAPEX or OPEX

    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_1_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
     to
    1.41
    ۰
    1.41
    dı
    1.14
     for
    1.12
    ０
    1.05
    inė
    1.02
    
    0.95
    inį
    0.93
    ᱐
    0.93
    television
    0.92
    POSITIVE LOGITS
    ל
    1.69
    و
    1.48
    س
    1.36
    In
    1.31
    ر
    1.29
    ن
    1.26
    ו
    1.24
    ل
    1.17
    ق
    1.14
    ש
    1.12
    Activations Density 0.001%

    No Known Activations