© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41777
    Prev
    Next
    INDEX
    Explanations

    postcode identifiers

    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
    is
    0.78
    n
    0.74
    문의
    0.62
    ี
    0.61
    x
    0.60
     bolesti
    0.57
     kurie
    0.55
    and
    0.54
     นั้น
    0.54
    மற்ற
    0.54
    POSITIVE LOGITS
    ри
    0.70
     (
    0.67
     the
    0.64
    一
    0.63
     Championship
    0.59
    き
    0.59
     infractions
    0.59
     Наи
    0.58
    1
    0.57
     are
    0.57
    Activations Density 0.003%

    No Known Activations