© 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. 31749
    Prev
    Next
    INDEX
    Explanations

    Ukraine recipes

    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
    uerre
    0.42
    <0x89>
    0.39
    gera
    0.38
    jala
    0.38
     जानी
    0.37
    твра
    0.36
     پائی
    0.36
     coiled
    0.36
     শ্যাম
    0.36
    oxo
    0.36
    POSITIVE LOGITS
     Су
    0.55
     NV
    0.55
     Sus
    0.53
    Sus
    0.49
    NV
    0.49
    Susp
    0.48
     D
    0.47
    Су
    0.46
     苏
    0.45
    susp
    0.44
    Activations Density 0.003%

    No Known Activations