© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1982
    Prev
    Next
    INDEX
    Explanations

    Http, Models, Helpers

    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_40_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
    Arche
    0.38
     codimension
    0.36
    渭
    0.35
    arche
    0.35
     ওয়ে
    0.34
    ングル
    0.34
    淐
    0.34
    BC
    0.34
    庫
    0.34
     Arche
    0.33
    POSITIVE LOGITS
     مدل
    0.49
     систе
    0.41
     системой
    0.39
    কুট
    0.39
    System
    0.38
    syst
    0.38
     effekt
    0.38
     syst
    0.37
    モデル
    0.37
    ระบบ
    0.37
    Activations Density 0.000%

    No Known Activations