© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236761
    Prev
    Next
    INDEX
    Explanations

    life vests

    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
    金
    0.48
     knots
    0.46
     knot
    0.42
     knotted
    0.42
    金の
    0.41
    金を
    0.39
    зяржа
    0.39
    жей
    0.38
     đọc
    0.38
    号
    0.38
    POSITIVE LOGITS
    Unity
    0.40
    Kitty
    0.39
     Stability
    0.39
     unity
    0.38
     विद्यार्थियों
    0.38
    bouncer
    0.38
    Personnel
    0.38
    ্লাই
    0.38
    bran
    0.38
     Unity
    0.37
    Activations Density 0.001%

    No Known Activations