© 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. 90253
    Prev
    Next
    INDEX
    Explanations

    protection plans, payment plans, penalty kicks

    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
     a
    1.05
    s
    0.94
    a
    0.83
    K
    0.82
     an
    0.78
    j
    0.77
    L
    0.75
    是
    0.75
     that
    0.72
    N
    0.72
    POSITIVE LOGITS
    ج
    0.69
    اليه
    0.63
    ierry
    0.60
    اسية
    0.59
     اكثر
    0.59
    نيف
    0.59
    يروس
    0.57
    ال
    0.57
    wakilan
    0.57
    بير
    0.56
    Activations Density 0.000%

    No Known Activations