© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217204
    Prev
    Next
    INDEX
    Explanations

    black

    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
     black
    0.51
     Black
    0.48
    BLACK
    0.46
     sized
    0.45
     BLACK
    0.45
     Grey
    0.43
    Grey
    0.43
    黑
    0.42
     ever
    0.42
     grey
    0.41
    POSITIVE LOGITS
    varian
    0.41
     ارت
    0.38
    ピオン
    0.38
     الصحي
    0.37
    ipse
    0.36
    orrag
    0.36
    ätze
    0.36
    ్ర
    0.36
    ASCII
    0.36
    hai
    0.35
    Activations Density 0.001%

    No Known Activations