© 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. 34577
    Prev
    Next
    INDEX
    Explanations

    Low Latency

    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
    ل
    0.86
    ry
    0.82
    man
    0.82
    min
    0.79
    st
    0.78
    mol
    0.77
    ال
    0.73
    m
    0.73
    machines
    0.73
    meng
    0.71
    POSITIVE LOGITS
    는
    0.88
     a
    0.82
    是
    0.82
     bo
    0.79
     valori
    0.73
     sobre
    0.73
     transporte
    0.72
    は
    0.72
     be
    0.71
     través
    0.71
    Activations Density 0.009%

    No Known Activations