© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10063
    Prev
    Next
    INDEX
    Explanations

    all-wheel drive

    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_13_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
    ar
    0.26
    f
    0.24
    et
    0.23
    ons
    0.22
    aw
    0.22
    ade
    0.21
    t
    0.21
    op
    0.21
    ceptar
    0.21
    g
    0.21
    POSITIVE LOGITS
    这句话
    0.24
     questo
    0.22
     මෙය
    0.22
     скорость
    0.22
     abolish
    0.21
     спор
    0.21
     هذا
    0.21
     исследова
    0.21
     конструк
    0.21
     сне
    0.21
    Activations Density 0.032%

    No Known Activations