© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 235805
    Prev
    Next
    INDEX
    Explanations

    text markers

    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_46_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
     pws
    0.39
    beros
    0.39
    সূরা
    0.38
     fxaa
    0.38
    дини
    0.38
     sideWeight
    0.37
     damos
    0.37
    爍
    0.37
     నేను
    0.37
     provenant
    0.37
    POSITIVE LOGITS
     ඇ
    0.59
     א
    0.58
     ﺍ
    0.57
     ار
    0.56
     อ
    0.55
     الا
    0.54
    ඇ
    0.53
    อาจ
    0.52
     اش
    0.52
     اب
    0.51
    Activations Density 0.080%

    No Known Activations