© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93528
    Prev
    Next
    INDEX
    Explanations

    multi-tool or tools

    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_11_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
    考古
    0.60
     evaluates
    0.56
    能力
    0.53
     kt
    0.52
    ικ
    0.51
     fath
    0.50
     ọ
    0.50
    此
    0.50
    ﺤ
    0.50
    γι
    0.49
    POSITIVE LOGITS
    cenik
    0.63
     שנ
    0.56
    camb
    0.55
    ulio
    0.55
     ತ
    0.54
    ciones
    0.53
     рынке
    0.52
     seaweed
    0.52
     שני
    0.52
    unuh
    0.52
    Activations Density 0.003%

    No Known Activations