© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14108
    Prev
    Next
    INDEX
    Explanations

    shift, kubernetes, container, cluster

    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_15_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
     ኢ
    0.60
     വരുന്ന
    0.59
     स्वरूप
    0.55
     전문
    0.55
    "%
    0.55
     ദൈവ
    0.53
     بإ
    0.52
    <unused266>
    0.52
    <unused1915>
    0.52
     പരി
    0.51
    POSITIVE LOGITS
    Soda
    0.63
    Donate
    0.63
    Sugar
    0.61
    Operator
    0.61
    Generalized
    0.59
    Berikut
    0.58
    Do
    0.57
    ;
    0.56
    Todas
    0.55
    Background
    0.54
    Activations Density 0.009%

    No Known Activations