© 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. 39137
    Prev
    Next
    INDEX
    Explanations

    checking on

    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
    2
    0.80
    us
    0.79
    的
    0.70
    d
    0.67
    Ли
    0.66
    ว่า
    0.64
    וס
    0.64
    et
    0.64
    =>
    0.64
    كد
    0.64
    POSITIVE LOGITS
    for
    0.81
    ことを
    0.77
    ners
    0.76
    یت
    0.74
    ն
    0.73
    ments
    0.71
    نی
    0.69
    ना
    0.68
     도시
    0.68
     it
    0.68
    Activations Density 0.001%

    No Known Activations