© 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. 90666
    Prev
    Next
    INDEX
    Explanations

    dev or http

    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
    as
    0.79
    in
    0.74
    i
    0.71
    Y
    0.68
     synthes
    0.67
    target
    0.67
    task
    0.66
    tries
    0.65
    weichen
    0.65
    د
    0.63
    POSITIVE LOGITS
    ING
    0.62
    િ
    0.62
    ımız
    0.60
     o
    0.59
    és
    0.59
     Meadow
    0.59
    ');
    0.58
    ం
    0.57
     spettacolo
    0.56
    <unused70>
    0.56
    Activations Density 0.001%

    No Known Activations