© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50726
    Prev
    Next
    INDEX
    Explanations

    lollipop and anti-androgen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    ckiego
    0.63
     Китай
    0.60
    >";
    0.59
     غير
    0.58
    kých
    0.58
    ية
    0.57
    ic
    0.56
    ';"+
    0.55
     Đài
    0.55
    '>";
    0.54
    POSITIVE LOGITS
    ↵↵
    0.57
    o
    0.57
      
    0.54
     me
    0.50
     hars
    0.50
     in
    0.48
     yo
    0.47
    <0x0D>
    0.46
     comme
    0.46
    נה
    0.46
    Activations Density 0.000%

    No Known Activations