© 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
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 68817
    Prev
    Next
    INDEX
    Explanations

    call to action

    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
     please
    0.43
     请
    0.40
    idente
    0.40
    Please
    0.39
    請
    0.38
    引用
    0.38
     Cig
    0.38
    iaire
    0.38
     Please
    0.38
     Nek
    0.37
    POSITIVE LOGITS
    Activate
    0.41
    ^)
    0.40
    Time
    0.39
    标准化
    0.39
    Do
    0.39
    時間の
    0.38
     Tell
    0.37
     подо
    0.36
     Гуляць
    0.36
    Get
    0.35
    Activations Density 0.024%

    No Known Activations