© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42947
    Prev
    Next
    INDEX
    Explanations

    Object-Relational Mapping (ORM)

    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_3_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
    '
    0.80
    ру
    0.63
     that
    0.61
    aż
    0.58
    ou
    0.57
    ने
    0.56
    れる
    0.56
    ومي
    0.56
    郁
    0.56
    ర
    0.55
    POSITIVE LOGITS
    ル
    0.64
    $("
    0.60
    kost
    0.59
    𒁀
    0.59
     осуществ
    0.59
    nico
    0.57
    inu
    0.56
    あった
    0.56
    lz
    0.55
     изготов
    0.55
    Activations Density 0.011%

    No Known Activations