© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228760
    Prev
    Next
    INDEX
    Explanations

    to purpose

    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_6_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
    ۴
    0.88
    ется
    0.86
    ３
    0.75
    、「
    0.74
    ");
    0.73
     seguir
    0.71
    ’
    0.71
    ၊
    0.69
    '
    0.68
    は
    0.68
    POSITIVE LOGITS
    t
    1.01
    u
    0.96
    as
    0.93
    o
    0.91
    d
    0.89
    on
    0.88
    i
    0.87
    im
    0.86
     buds
    0.81
    a
    0.80
    Activations Density 0.001%

    No Known Activations