© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54151
    Prev
    Next
    INDEX
    Explanations

    regular

    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_55_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
     CHAIRMAN
    0.37
     Lynda
    0.35
    Checks
    0.35
     उपचुनाव
    0.35
    塞
    0.35
    ниц
    0.34
    checker
    0.34
    䅧
    0.34
    --;
    0.33
    蛹
    0.33
    POSITIVE LOGITS
     regular
    3.05
    Regular
    2.89
    regular
    2.81
     регуляр
    2.80
     Regular
    2.75
     regularly
    2.55
     नियमित
    2.55
     regulares
    2.42
    定期
    2.38
     Regularly
    2.33
    Activations Density 0.032%

    No Known Activations