© 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. 45972
    Prev
    Next
    INDEX
    Explanations

    molecular bridge and match pair

    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
    ;
    0.89
    ,
    0.78
    .,
    0.74
    ;"
    0.69
    nine
    0.64
    );
    0.62
    Zr
    0.61
    ;'
    0.61
    ';
    0.60
    ;,
    0.60
    POSITIVE LOGITS
    その
    0.75
     cria
    0.71
     cré
    0.66
     sarà
    0.66
     creen
    0.66
    み
    0.64
     vigilancia
    0.62
    ការពារ
    0.61
     será
    0.61
    看来
    0.60
    Activations Density 0.001%

    No Known Activations