© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49452
    Prev
    Next
    INDEX
    Explanations

    HTML structure

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    hInstance
    0.44
    parser
    0.40
     strtotime
    0.38
    patial
    0.37
     '"
    0.37
     hInstance
    0.37
     phúc
    0.37
    滞
    0.36
     thủ
    0.35
    sql
    0.35
    POSITIVE LOGITS
    Wrapped
    0.40
     atleast
    0.38
     সম্পর্কিত
    0.38
    Hide
    0.37
    Más
    0.37
    Sobre
    0.37
     demost
    0.37
    Bold
    0.36
    Show
    0.36
     रिलेटेड
    0.36
    Activations Density 0.003%

    No Known Activations