© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32928
    Prev
    Next
    INDEX
    Explanations

    mac

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ModelComponent
    0.45
    x
    0.43
    iland
    0.40
    xC
    0.37
     Иль
    0.37
     আকাশ
    0.36
    護
    0.36
    X
    0.35
    𝒙
    0.35
     आदर्श
    0.34
    POSITIVE LOGITS
    loess
    0.42
    阿拉伯
    0.39
    usher
    0.38
    ufen
    0.38
    ologische
    0.38
    coh
    0.38
    واف
    0.38
    йти
    0.36
     diện
    0.36
    DOF
    0.36
    Activations Density 0.002%

    No Known Activations