© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 197387
    Prev
    Next
    INDEX
    Explanations

    decency

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    realpath
    0.36
    доль
    0.35
    GCG
    0.34
    㐬
    0.34
    Sin
    0.34
     мастер
    0.33
    İK
    0.33
    FAO
    0.33
     Верхов
    0.33
    ㎞
    0.33
    POSITIVE LOGITS
     decent
    2.69
     decency
    1.69
     decently
    1.66
     Dec
    1.54
    Dec
    1.34
     respectable
    1.16
     dec
    1.13
     déc
    1.04
    dec
    1.02
     DEC
    1.02
    Activations Density 0.126%

    No Known Activations