© 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. 87132
    Prev
    Next
    INDEX
    Explanations

    building in

    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
    a
    0.90
    ه
    0.71
     spettac
    0.69
    i
    0.69
    an
    0.67
    in
    0.66
    
    0.66
    herlands
    0.66
    inspiration
    0.64
    iiv
    0.64
    POSITIVE LOGITS
    ला
    0.83
    เป็น
    0.77
     to
    0.72
    લ
    0.66
    на
    0.66
    िस
    0.65
    ले
    0.62
     INTO
    0.62
     be
    0.61
    ם
    0.60
    Activations Density 0.000%

    No Known Activations