© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62399
    Prev
    Next
    INDEX
    Explanations

    Thomas followed by a surname

    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_2_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
    is
    1.48
    in
    1.38
    ни
    1.17
    are
    1.06
    on
    1.02
    ா
    0.97
    has
    0.95
    am
    0.94
    <0x0D>
    0.91
    ಿ
    0.88
    POSITIVE LOGITS
    soever
    0.98
    ünde
    0.88
     azienda
    0.82
    üne
    0.80
    ন
    0.79
    সা
    0.78
    üd
    0.78
    وم
    0.77
     că
    0.76
     cidade
    0.76
    Activations Density 0.003%

    No Known Activations