© 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. 37722
    Prev
    Next
    INDEX
    Explanations

    X11 Window System configuration

    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
     febru
    0.72
    o
    0.71
    ة
    0.69
    ことで
    0.64
     procent
    0.64
     mozz
    0.64
     polinom
    0.62
    ing
    0.61
     rơi
    0.60
    有限公司
    0.58
    POSITIVE LOGITS
    ד
    0.69
    t
    0.67
    dc
    0.64
    اد
    0.62
     (
    0.61
    A
    0.61
    ל
    0.59
    database
    0.59
    daki
    0.59
    density
    0.58
    Activations Density 0.011%

    No Known Activations