© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40852
    Prev
    Next
    INDEX
    Explanations

    python libraries like libtorrent, librosa

    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
    it
    1.02
    and
    0.79
    as
    0.77
    at
    0.76
    ী
    0.75
    ie
    0.71
    ا
    0.70
    </h2>
    0.70
    é
    0.70
    em
    0.68
    POSITIVE LOGITS
    '
    0.73
    は
    0.68
     is
    0.65
    ي
    0.60
    ク
    0.60
     manière
    0.59
    ked
    0.59
     plein
    0.57
     шрифт
    0.55
     inscr
    0.55
    Activations Density 0.005%

    No Known Activations