© 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. 198486
    Prev
    Next
    INDEX
    Explanations

    conditions, due, the, w, 0, a, second

    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
     objek
    0.49
    EXAMPLE
    0.49
    тивов
    0.49
     സംഘടന
    0.48
    棪
    0.48
     podia
    0.48
     ringan
    0.47
    క్షన్
    0.47
    দ্দিক
    0.46
    _
    0.46
    POSITIVE LOGITS
    ا
    0.47
    ijan
    0.46
    ij
    0.46
    ک
    0.46
    ijker
    0.46
     AW
    0.45
     সুরে
    0.43
     продовжу
    0.43
    ي
    0.43
    ج
    0.42
    Activations Density 0.000%

    No Known Activations