© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194734
    Prev
    Next
    INDEX
    Explanations

    sampler options

    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_15_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
    くなる
    0.51
     Л
    0.50
     экстре
    0.50
     hiểu
    0.49
     Д
    0.48
    ても
    0.47
    す
    0.47
     су
    0.47
    зна
    0.46
    ש
    0.45
    POSITIVE LOGITS
    ork
    0.56
    ot
    0.55
    us
    0.54
    ords
    0.52
    nms
    0.52
    ungy
    0.51
    und
    0.50
    hh
    0.50
     papp
    0.49
    ulla
    0.49
    Activations Density 0.000%

    No Known Activations