© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47630
    Prev
    Next
    INDEX
    Explanations

    passage of text

    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_10_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
     يمكن
    0.69
     бесплат
    0.68
    ي
    0.68
    يب
    0.67
    6
    0.67
     كم
    0.67
     التي
    0.66
     الذين
    0.66
    ното
    0.66
    inde
    0.65
    POSITIVE LOGITS
    A
    0.76
     Lune
    0.64
    তী
    0.61
    Isl
    0.56
     protagon
    0.56
     sobie
    0.56
    侔
    0.55
     haunting
    0.55
     biomarker
    0.54
     Lanier
    0.54
    Activations Density 0.002%

    No Known Activations