© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205482
    Prev
    Next
    INDEX
    Explanations

    boot

    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_46_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
     nghiên
    0.42
     lifted
    0.39
    stressed
    0.39
    IEC
    0.38
    cotton
    0.37
     مسائل
    0.37
     oti
    0.36
    ԝ
    0.36
     lifting
    0.35
    Lift
    0.35
    POSITIVE LOGITS
    أة
    0.44
     Cere
    0.40
    ubre
    0.40
    feeds
    0.38
    ého
    0.38
     extrad
    0.38
    feed
    0.37
    idere
    0.37
    れていた
    0.37
    عة
    0.37
    Activations Density 0.001%

    No Known Activations