© 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. 89569
    Prev
    Next
    INDEX
    Explanations

    vas deferens

    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
    nél
    0.77
    ስ
    0.77
     possibilit
    0.76
    0
    0.72
    ۰
    0.70
    rom
    0.69
    sou
    0.68
    sr
    0.67
    s
    0.67
    ﺝ
    0.66
    POSITIVE LOGITS
    是
    0.79
    ى
    0.78
    يد
    0.67
    。
    0.67
    يين
    0.67
    ך
    0.66
    Jähr
    0.65
    قي
    0.64
    ت
    0.61
     (
    0.60
    Activations Density 0.001%

    No Known Activations