© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 198307
    Prev
    Next
    INDEX
    Explanations

    general population

    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_4_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
    ки
    0.85
    ی
    0.84
    ா
    0.83
    atoare
    0.81
     répart
    0.80
    ים
    0.79
    ų
    0.77
    watercolor
    0.75
    кати
    0.75
    новый
    0.74
    POSITIVE LOGITS
    ;
    0.90
     a
    0.89
     en
    0.86
     o
    0.81
     for
    0.77
     אי
    0.77
     u
    0.74
     I
    0.70
     Э
    0.70
     og
    0.69
    Activations Density 0.000%

    No Known Activations