© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233177
    Prev
    Next
    INDEX
    Explanations

    SAL

    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_32_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
     Shelf
    0.29
    Vis
    0.27
     सद
    0.26
     vertically
    0.26
    Shelf
    0.26
     образом
    0.26
     الزد
    0.26
    Ĭ
    0.26
     Permalink
    0.26
     resources
    0.25
    POSITIVE LOGITS
     risque
    0.29
     eliminar
    0.27
     warna
    0.27
     termino
    0.27
     asociado
    0.26
     capitol
    0.26
    Capitol
    0.26
     बच्ची
    0.26
    inoza
    0.26
     pout
    0.25
    Activations Density 0.002%

    No Known Activations