© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40931
    Prev
    Next
    INDEX
    Explanations

    quarter, hours, combat, Circle Ranch

    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_3_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
    k
    0.78
    жи
    0.75
    kron
    0.71
    kde
    0.70
    み
    0.70
    kons
    0.70
    그러
    0.66
    ко
    0.65
    LayoutStyle
    0.65
    kA
    0.65
    POSITIVE LOGITS
     quarter
    1.01
     to
    0.97
     Quarter
    0.94
     quart
    0.93
     Quart
    0.90
    Quarter
    0.89
    {
    0.86
     r
    0.80
     have
    0.80
     not
    0.80
    Activations Density 0.010%

    No Known Activations