© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140903
    Prev
    Next
    INDEX
    Explanations

    this isn't

    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_12_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
    ut
    0.81
    yi
    0.76
    s
    0.74
    t
    0.72
    listening
    0.67
    ling
    0.62
    and
    0.62
    tourism
    0.62
    ing
    0.61
    making
    0.61
    POSITIVE LOGITS
     dépôt
    0.70
     égal
    0.66
    ပေါ
    0.63
    ן
    0.61
     ép
    0.59
     nouvel
    0.59
     可
    0.59
     一个
    0.58
    ዥ
    0.58
     اذا
    0.57
    Activations Density 0.007%

    No Known Activations