© 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. 90123
    Prev
    Next
    INDEX
    Explanations

    Royal Caribbean

    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
    ด
    0.88
    с
    0.78
    a
    0.75
    न
    0.74
    ス
    0.73
    д
    0.72
    스
    0.72
    ك
    0.71
    ل
    0.70
    د
    0.69
    POSITIVE LOGITS
     is
    0.82
    ist
    0.77
    ן
    0.65
    ää
    0.59
    ým
    0.55
    iting
    0.54
    ية
    0.54
    ą
    0.53
    ग्विजय
    0.52
    icer
    0.52
    Activations Density 0.002%

    No Known Activations