© 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. 39436
    Prev
    Next
    INDEX
    Explanations

    omial, omon endings

    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
    мма
    0.69
    ну
    0.66
    филлер
    0.66
    imizi
    0.66
    지
    0.65
     Tattha
    0.64
    во
    0.64
    ק
    0.64
    важа
    0.63
    ీ
    0.63
    POSITIVE LOGITS
     it
    0.81
     I
    0.80
    त
    0.75
     group
    0.68
     diagonal
    0.65
     slave
    0.64
     watchdog
    0.63
     by
    0.62
     symbol
    0.62
     Trin
    0.62
    Activations Density 0.000%

    No Known Activations