© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134115
    Prev
    Next
    INDEX
    Explanations

    pandas data types and missing values

    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_37_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
    ってください
    0.41
     কর্তৃ
    0.39
     Surya
    0.38
    釵
    0.38
    ρίες
    0.38
     Organisation
    0.37
    ρές
    0.37
     overcrowded
    0.37
    सूर्य
    0.37
     Bit
    0.36
    POSITIVE LOGITS
    getStock
    0.41
     underlying
    0.35
     Incl
    0.35
     Woh
    0.35
    训
    0.34
    غو
    0.34
     entendimento
    0.34
    दर्
    0.33
     handouts
    0.33
     Stock
    0.33
    Activations Density 0.002%

    No Known Activations