© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28007
    Prev
    Next
    INDEX
    Explanations

    subaru legacy, forester, brz, bg

    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
    of
    0.74
    v
    0.70
    b
    0.66
    nd
    0.65
    ك
    0.64
    that
    0.63
    RIES
    0.60
     Políticas
    0.60
    áp
    0.59
    ريبا
    0.59
    POSITIVE LOGITS
    ু
    0.73
     interstitiis
    0.70
     mirip
    0.69
     conifers
    0.68
     pubs
    0.68
     д
    0.68
     vix
    0.65
     автомобилей
    0.65
    </h3>
    0.64
     étamines
    0.64
    Activations Density 0.003%

    No Known Activations