© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156660
    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_2_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
     of
    0.98
    вання
    0.86
    <0x0D>
    0.85
    {
    0.81
    '
    0.74
    im
    0.73
    '");
    0.72
    \,\
    0.68
     deliberations
    0.68
    StructOf
    0.68
    POSITIVE LOGITS
    v
    1.02
    ли
    0.98
    c
    0.97
    re
    0.96
    ق
    0.96
    时
    0.93
    la
    0.92
    に
    0.92
    f
    0.91
    r
    0.88
    Activations Density 0.000%

    No Known Activations