© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207304
    Prev
    Next
    INDEX
    Explanations

    constructor

    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_19_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
     ओनली
    0.47
    㗽
    0.44
     alcoved
    0.43
     ምክንያት
    0.43
    υπ
    0.42
    ్యం
    0.42
    steal
    0.42
    сез
    0.42
    ชัด
    0.41
    нет
    0.41
    POSITIVE LOGITS
    aisu
    0.41
     Supervision
    0.41
    服務
    0.39
    adaan
    0.38
    有着
    0.38
    bali
    0.38
     c
    0.37
    avant
    0.37
     Estat
    0.37
    サービスの
    0.36
    Activations Density 0.002%

    No Known Activations