© 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. 39185
    Prev
    Next
    INDEX
    Explanations

    varying degrees of

    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
    もら
    0.68
    I
    0.62
    ো
    0.62
    에서는
    0.61
    tų
    0.60
    ların
    0.60
    daki
    0.60
    dimensioni
    0.59
    separation
    0.59
    Separ
    0.58
    POSITIVE LOGITS
     to
    0.76
    هم
    0.68
     is
    0.68
    વ
    0.66
     ,
    0.62
    ني
    0.60
    瓈
    0.60
     i
    0.58
     win
    0.58
     alimentar
    0.56
    Activations Density 0.003%

    No Known Activations