© 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. 36540
    Prev
    Next
    INDEX
    Explanations

    list item marker

    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
    ×
    0.61
     ×
    0.56
    ☓
    0.39
    ✘
    0.39
    
    0.38
    〆
    0.38
    ❎
    0.38
     Han
    0.37
    >×</
    0.37
    ✕
    0.36
    POSITIVE LOGITS
     Initiative
    0.39
     precision
    0.38
    precision
    0.38
    Two
    0.38
    Precision
    0.38
    ୯
    0.38
     প্রতিমন্ত্রী
    0.38
    ሶ
    0.38
    wys
    0.38
    }$-
    0.37
    Activations Density 0.002%

    No Known Activations