© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34362
    Prev
    Next
    INDEX
    Explanations

    Ed Sheeran

    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_3_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
    ü
    0.78
    не
    0.69
     FACT
    0.62
    ू
    0.61
    ă
    0.57
    ளவில்
    0.57
    ı
    0.56
    INTa
    0.56
    ında
    0.55
    UNT
    0.55
    POSITIVE LOGITS
    is
    0.78
    ق
    0.73
    isering
    0.68
    का
    0.68
    Time
    0.67
    ث
    0.65
    isely
    0.63
    isah
    0.62
    al
    0.61
    Color
    0.61
    Activations Density 0.003%

    No Known Activations