© 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. 89426
    Prev
    Next
    INDEX
    Explanations

    localization and language

    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
     YouTube
    0.83
     internet
    0.80
     Twitter
    0.79
     Amazon
    0.78
     y
    0.78
     iOS
    0.76
     Instagram
    0.75
     intranet
    0.75
     Vimeo
    0.74
     Facebook
    0.71
    POSITIVE LOGITS
    Ships
    0.60
    OF
    0.57
    ByMerging
    0.55
    AN
    0.54
    и
    0.53
    ShaderType
    0.53
    OR
    0.52
    ENUM
    0.52
    IGR
    0.52
    OfDay
    0.52
    Activations Density 0.034%

    No Known Activations