© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199836
    Prev
    Next
    INDEX
    Explanations

    transfer or change

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     shaft
    0.63
     ша
    0.60
    샤
    0.60
    Ша
    0.59
     shafts
    0.59
    ша
    0.57
     Ша
    0.57
     샤
    0.57
    sha
    0.57
    Sha
    0.56
    POSITIVE LOGITS
     пере
    1.16
    Пере
    0.93
    пере
    0.90
     Пере
    0.89
     chuyển
    0.71
     пера
    0.61
     pere
    0.59
     TRANSFER
    0.58
    転
    0.56
     pā
    0.54
    Activations Density 0.032%

    No Known Activations