© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123965
    Prev
    Next
    INDEX
    Explanations

    covariance matrix

    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
     увеличи
    0.68
    <0xF3>
    0.63
     chuột
    0.61
     przeprowad
    0.60
     примерно
    0.60
     conduire
    0.59
     dolore
    0.59
     conocida
    0.58
     деп
    0.58
     опубликован
    0.58
    POSITIVE LOGITS
    ص
    0.93
    ح
    0.83
    ل
    0.80
    س
    0.79
    ج
    0.75
    ش
    0.74
    म
    0.73
    at
    0.72
    ف
    0.71
    ह
    0.68
    Activations Density 0.000%

    No Known Activations