© 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. 45541
    Prev
    Next
    INDEX
    Explanations

    Denon, Sequoia giganteum

    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
    细节
    0.73
    נ
    0.71
    ม
    0.71
    욘
    0.69
     détails
    0.67
    是为了
    0.67
     detal
    0.67
     dettagli
    0.67
    是
    0.66
     detalles
    0.66
    POSITIVE LOGITS
     for
    0.81
    িন
    0.77
    f
    0.75
    }"
    0.66
     Verge
    0.61
     a
    0.61
    for
    0.61
    }=-
    0.60
    }}"
    0.59
     kteří
    0.59
    Activations Density 0.001%

    No Known Activations