© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34565
    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_7_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
    s
    0.84
     to
    0.57
     notificações
    0.57
     lampu
    0.56
    ים
    0.55
    ों
    0.53
     catatan
    0.50
     бир
    0.50
     Гинд
    0.50
    скую
    0.49
    POSITIVE LOGITS
    :
    0.57
     ומ
    0.55
    לי
    0.51
    {
    0.50
    ColorScheme
    0.50
    ო
    0.48
    POLICY
    0.47
    伍章
    0.47
    Execution
    0.46
    ิ
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.