© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97155
    Prev
    Next
    INDEX
    Explanations

    art mediums and supplies

    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_14_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
     :
    0.37
    ={"
    0.35
     :,
    0.35
     ,"
    0.33
     :"
    0.32
     :");
    0.32
     studente
    0.31
    修行
    0.30
     ."
    0.30
     Biennale
    0.30
    POSITIVE LOGITS
    TERS
    0.37
    ᒻ
    0.34
     locaux
    0.32
     véhicules
    0.32
    ñas
    0.32
    able
    0.31
     oyster
    0.31
    owler
    0.31
     inventions
    0.30
    ymas
    0.30
    Activations Density 0.002%

    No Known Activations