© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231704
    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_6_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
    t
    1.42
    The
    1.04
    the
    1.02
    of
    1.01
    ของ
    0.99
     of
    0.97
    nya
    0.96
    ın
    0.93
    st
    0.90
    кі
    0.89
    POSITIVE LOGITS
    ك
    1.11
    م
    1.08
    at
    0.95
     ovales
    0.90
     lanz
    0.87
     ে
    0.86
    كيف
    0.85
    يروس
    0.84
    ياب
    0.83
    اريخ
    0.83
    Activations Density 0.000%

    No Known Activations