© 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. 47987
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    eské
    0.86
    h
    0.80
    endtime
    0.80
    يطان
    0.79
    hite
    0.77
     tartoz
    0.76
    enciais
    0.74
     άνθρω
    0.73
    akra
    0.72
    ično
    0.71
    POSITIVE LOGITS
     but
    0.92
     to
    0.84
    ร
    0.82
    ै
    0.81
    ד
    0.80
     be
    0.79
     saw
    0.78
    ف
    0.77
    ка
    0.76
     '
    0.76
    Activations Density 0.000%

    No Known Activations