© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100348
    Prev
    Next
    INDEX
    Explanations

    assignments, presentations, heaters, dumps

    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_16_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
    ong
    0.70
    C
    0.68
    y
    0.68
    an
    0.61
    ang
    0.58
    a
    0.57
    ru
    0.57
    yl
    0.57
    ходов
    0.57
    hor
    0.56
    POSITIVE LOGITS
    ಾರ್
    0.55
    ू
    0.55
     tha
    0.54
    锑
    0.54
    嘛
    0.54
     implicit
    0.52
     anticipating
    0.52
     setDescription
    0.52
     allt
    0.51
     describing
    0.51
    Activations Density 0.000%

    No Known Activations