© 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. 91271
    Prev
    Next
    INDEX
    Explanations

    Kullback-Leibler divergence

    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
    of
    0.66
     of
    0.65
    在
    0.59
    有
    0.59
    会
    0.59
     dreamt
    0.57
     dide
    0.56
     че
    0.55
     гру
    0.55
    可以让
    0.55
    POSITIVE LOGITS
    ين
    0.70
    U
    0.70
    AY
    0.66
    서
    0.64
    EN
    0.63
    Ur
    0.63
    정
    0.63
    uk
    0.62
    AG
    0.61
    EX
    0.60
    Activations Density 0.000%

    No Known Activations