© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149365
    Prev
    Next
    INDEX
    Explanations

    sine function

    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_59_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
    >${
    0.38
    :${
    0.37
    Input
    0.36
    %
    0.36
    כם
    0.35
    视为
    0.34
    BuildActionEntry
    0.34
    어
    0.33
    વ
    0.33
    ך
    0.33
    POSITIVE LOGITS
     sin
    1.00
     sina
    0.85
     sinus
    0.85
     Sin
    0.84
    sin
    0.82
    Sin
    0.82
     SIN
    0.82
     sine
    0.81
    SIN
    0.76
     sinusoidal
    0.74
    Activations Density 0.001%

    No Known Activations