© 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. 90145
    Prev
    Next
    INDEX
    Explanations

    entry point

    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
    unidad
    0.77
    س
    0.76
    ização
    0.68
     بأ
    0.67
    となった
    0.65
    aš
    0.65
    艨
    0.62
    حة
    0.61
    éges
    0.60
     système
    0.59
    POSITIVE LOGITS
    the
    0.94
     in
    0.76
    th
    0.73
    들이
    0.68
    in
    0.63
    tta
    0.62
    지
    0.60
    ld
    0.59
    8
    0.59
    지만
    0.59
    Activations Density 0.011%

    No Known Activations