© 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. 39154
    Prev
    Next
    INDEX
    Explanations

    sun exposure or sunburst

    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
    an
    0.82
    ای
    0.68
     عزیز
    0.67
    COUNT
    0.61
     nowych
    0.59
    用の
    0.59
    १
    0.59
     μια
    0.59
    ลูก
    0.58
     میزان
    0.58
    POSITIVE LOGITS
    س
    0.70
    lections
    0.70
    рить
    0.69
    رج
    0.65
    ركة
    0.63
    fice
    0.63
    ثير
    0.62
    دا
    0.62
    itäts
    0.61
    kbar
    0.61
    Activations Density 0.002%

    No Known Activations