© 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. 127343
    Prev
    Next
    INDEX
    Explanations

    lost and opportunities

    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
    上
    0.75
    كل
    0.75
    C
    0.75
    ఎ
    0.74
    లో
    0.73
    *}
    0.73
    ل
    0.72
    EventHandler
    0.72
    лк
    0.72
    л
    0.72
    POSITIVE LOGITS
    ed
    0.95
     for
    0.89
    <0x80>
    0.81
    t
    0.76
     perdu
    0.70
     loss
    0.69
     signatory
    0.69
    ओं
    0.69
     topographical
    0.68
     isomer
    0.66
    Activations Density 0.002%

    No Known Activations