© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58435
    Prev
    Next
    INDEX
    Explanations

    word endings like er, ed, ing

    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_2_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
    to
    1.88
    ى
    1.68
    وم
    1.55
    ير
    1.46
    ra
    1.42
    ا
    1.39
    ó
    1.34
    ри
    1.28
    أ
    1.28
    다
    1.23
    POSITIVE LOGITS
     bravely
    0.90
    ков
    0.89
    dine
    0.84
     legalize
    0.81
     eaten
    0.80
    IANS
    0.79
    MER
    0.79
    pecific
    0.79
    :‏
    0.79
     perceptible
    0.77
    Activations Density 0.008%

    No Known Activations