© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45831
    Prev
    Next
    INDEX
    Explanations

    site center

    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_10_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
     sites
    0.79
    to
    0.71
    ai
    0.65
     s
    0.64
    ol
    0.64
    ic
    0.64
     locations
    0.64
    or
    0.63
     l
    0.63
     australia
    0.61
    POSITIVE LOGITS
     Sereth
    0.61
     Tanto
    0.57
    Πα
    0.55
    ле
    0.54
     Abubakar
    0.54
     Па
    0.54
    كد
    0.53
     Sunni
    0.53
     Danach
    0.53
     Jeder
    0.53
    Activations Density 0.019%

    No Known Activations