© 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. 86007
    Prev
    Next
    INDEX
    Explanations

    proceeding to

    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
    '
    0.69
    is
    0.67
     chops
    0.67
     valida
    0.66
     valore
    0.65
    é
    0.63
    ຜະລິດຕ
    0.62
    ۳
    0.62
    ⿰
    0.61
    ↵
    0.61
    POSITIVE LOGITS
    یل
    0.66
    ズ
    0.66
    procedure
    0.65
    proceed
    0.63
    ется
    0.62
    즈
    0.62
    嶋
    0.62
     geográfica
    0.61
     آسان
    0.61
    خ
    0.61
    Activations Density 0.001%

    No Known Activations