© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14805
    Prev
    Next
    INDEX
    Explanations

    nested text formatting

    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_13_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
    0.66
     in
    0.63
    -
    0.59
    width
    0.58
     optimizations
    0.57
    e
    0.55
     by
    0.54
    ge
    0.54
     developments
    0.54
    ’
    0.54
    POSITIVE LOGITS
     কমান্ড
    0.61
     Старки
    0.61
    記録
    0.60
     反
    0.60
     sér
    0.60
     входя
    0.60
     Mél
    0.59
     Comité
    0.59
     Спа
    0.59
     Hör
    0.59
    Activations Density 0.084%

    No Known Activations