© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48927
    Prev
    Next
    INDEX
    Explanations

    user-friendly interface

    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_10_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
    お
    0.84
    Ста
    0.84
    0
    0.81
    Дру
    0.80
    エ
    0.80
    した
    0.75
    یک
    0.74
    ZIONE
    0.74
    Пере
    0.73
    И
    0.73
    POSITIVE LOGITS
    "
    0.73
    iks
    0.65
    ecd
    0.64
    getMetering
    0.63
     dó
    0.63
    icism
    0.62
     cak
    0.62
    ien
    0.61
    reich
    0.61
    piel
    0.61
    Activations Density 0.004%

    No Known Activations