© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122989
    Prev
    Next
    INDEX
    Explanations

    ruggedness

    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_3_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
    را
    0.63
    ي
    0.59
     транспорта
    0.58
     показыва
    0.58
    ).}
    0.58
    ringen
    0.57
    ত্ত্ব
    0.56
    ла
    0.55
    ॉस
    0.55
    ps
    0.55
    POSITIVE LOGITS
    en
    0.61
    ור
    0.61
    ا
    0.58
    ห
    0.57
    لها
    0.56
    จำ
    0.51
    ไม่ใช่
    0.51
    博物
    0.50
    ايا
    0.50
     Bantu
    0.50
    Activations Density 0.000%

    No Known Activations