© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56770
    Prev
    Next
    INDEX
    Explanations

    pointed

    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_11_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
    ot
    0.70
    ್‌
    0.69
    M
    0.69
     thinks
    0.68
    Genome
    0.68
     مشکل
    0.66
     σε
    0.66
    )،
    0.64
    R
    0.64
    L
    0.64
    POSITIVE LOGITS
    有
    0.66
    个
    0.63
    动
    0.63
    端
    0.62
    :
    0.61
    港
    0.61
     geográfica
    0.60
    控
    0.60
    g
    0.60
     dériv
    0.59
    Activations Density 0.002%

    No Known Activations