© 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. 41887
    Prev
    Next
    INDEX
    Explanations

    serial input/output

    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
    0.94
    ES
    0.87
    es
    0.73
    d
    0.70
    ind
    0.68
     is
    0.66
    ه
    0.66
    ’;
    0.65
    aldi
    0.65
     करणाऱ्या
    0.64
    POSITIVE LOGITS
    و
    0.84
    ل
    0.67
    ो
    0.65
    ו
    0.64
    ל
    0.64
    ো
    0.60
    ى
    0.59
    wch
    0.57
    м
    0.56
    觛
    0.56
    Activations Density 0.030%

    No Known Activations