© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 124867
    Prev
    Next
    INDEX
    Explanations

    San Marco, San Martín, San Ramon

    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
    AIN
    0.81
    y
    0.78
    S
    0.75
    u
    0.74
    s
    0.73
    k
    0.73
    IN
    0.71
    ব
    0.71
    X
    0.70
    IUS
    0.70
    POSITIVE LOGITS
    _
    0.75
    of
    0.73
    。
    0.71
    ೀ
    0.71
    ।
    0.69
    ма
    0.69
     appendices
    0.67
    ುತ್ತವೆ
    0.65
    ερμαν
    0.63
     commut
    0.62
    Activations Density 0.000%

    No Known Activations