© 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. 208068
    Prev
    Next
    INDEX
    Explanations

    category/subcategoryresource/resourcemanager.projectCreatorcustom_colors/font_colorroutes/make-routesusr/bin/envsecurity/ir.model

    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
     tová
    0.66
     відді
    0.66
     ജില്ലാ
    0.65
     diferenciar
    0.63
     വകു
    0.62
    /}{
    0.61
     cityscape
    0.60
     dunno
    0.59
     Jungkook
    0.59
    ठबंधन
    0.59
    POSITIVE LOGITS
    ه
    0.83
    at
    0.79
    is
    0.78
    e
    0.75
    '
    0.72
    ↵
    0.71
    c
    0.71
    ל
    0.70
    a
    0.70
    יש
    0.66
    Activations Density 0.012%

    No Known Activations