© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36309
    Prev
    Next
    INDEX
    Explanations

    exclude /排

    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
    互
    0.39
    洛
    0.39
    公
    0.38
    路
    0.37
    ින
    0.37
    ]">
    0.37
    印
    0.36
     tail
    0.36
     Circle
    0.36
     एनएस
    0.35
    POSITIVE LOGITS
    排
    0.78
     排
    0.75
    排出
    0.59
    排除
    0.53
    排放
    0.44
    exclude
    0.43
    拍
    0.43
     sıral
    0.42
    命
    0.42
     棚
    0.42
    Activations Density 0.016%

    No Known Activations