© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62305
    Prev
    Next
    INDEX
    Explanations

    compressed air

    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_11_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
    ،
    0.73
    toare
    0.69
    loaders
    0.69
    ᇁ
    0.69
    closures
    0.68
     ລັບ
    0.67
    dbcontext
    0.66
    गाह
    0.66
    жами
    0.65
    Evaluating
    0.64
    POSITIVE LOGITS
    w
    0.92
    :
    0.89
    '
    0.71
    t
    0.69
    n
    0.68
    }
    0.68
     I
    0.67
    ↵↵
    0.63
    ัก
    0.62
     un
    0.62
    Activations Density 0.013%

    No Known Activations