© 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. 45587
    Prev
    Next
    INDEX
    Explanations

    set theory or bits

    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
     پایین
    0.71
     covariance
    0.70
    ו
    0.69
     이미
    0.68
    m
    0.66
     maju
    0.65
    irittura
    0.64
     매우
    0.63
    وتی
    0.63
    ੇ
    0.63
    POSITIVE LOGITS
    在
    0.86
     في
    0.81
     in
    0.79
    ك
    0.71
    对于
    0.68
    ischen
    0.68
    ING
    0.67
     Energie
    0.67
     (
    0.66
    stelle
    0.66
    Activations Density 0.005%

    No Known Activations