© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34435
    Prev
    Next
    INDEX
    Explanations

    moderately

    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_50_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
     Treatments
    0.38
    /******/
    0.38
    ዱ
    0.36
     الفترة
    0.36
    シルエット
    0.36
    کات
    0.35
     சிகிச்ச
    0.34
     Alamo
    0.34
     HM
    0.34
    skjaer
    0.34
    POSITIVE LOGITS
     уме
    0.46
    yon
    0.43
    armes
    0.43
    arin
    0.43
    mines
    0.42
    涫
    0.40
    adamente
    0.39
    unia
    0.38
    ectar
    0.38
    range
    0.38
    Activations Density 0.001%

    No Known Activations