© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193698
    Prev
    Next
    INDEX
    Explanations

    resident manager or child son

    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_27_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
    ⴰ
    0.38
     Stephenson
    0.36
     লক্ষণ
    0.35
    жек
    0.35
    MouseButton
    0.35
     anton
    0.35
    guessing
    0.34
    Governor
    0.34
    änden
    0.34
    솎
    0.34
    POSITIVE LOGITS
     ಅಧಿಕ
    0.42
     Detail
    0.36
     শক্তিশালী
    0.35
     Exempl
    0.35
     живе
    0.34
     exemplary
    0.33
    }=(-
    0.33
     Ashley
    0.33
    ictwo
    0.33
     sécur
    0.33
    Activations Density 0.032%

    No Known Activations