© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39135
    Prev
    Next
    INDEX
    Explanations

    algebraic expressions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    Piece
    0.41
     erle
    0.41
    羚
    0.39
    Massachusetts
    0.39
    atrol
    0.38
    રણ
    0.37
     Shelter
    0.36
    Greater
    0.36
     Reduces
    0.36
     ነ
    0.36
    POSITIVE LOGITS
    pciones
    0.41
    inture
    0.40
    gado
    0.37
    );*/
    0.34
    eck
    0.34
    ânt
    0.33
     conditioned
    0.32
    ﺏ
    0.32
    ftime
    0.32
    hub
    0.32
    Activations Density 0.004%

    No Known Activations