© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125636
    Prev
    Next
    INDEX
    Explanations

    Vatican City

    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_3_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
    are
    0.91
    as
    0.85
    and
    0.79
    all
    0.78
    od
    0.73
    é
    0.71
    on
    0.71
    err
    0.70
    锜
    0.70
    its
    0.68
    POSITIVE LOGITS
    د
    0.73
    ل
    0.72
    к
    0.72
     isom
    0.70
    ه
    0.70
    ر
    0.68
     duplo
    0.64
    ক
    0.64
    ่
    0.64
     самое
    0.64
    Activations Density 0.000%

    No Known Activations