© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26209
    Prev
    Next
    INDEX
    Explanations

    wired

    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_10_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
    ма
    0.91
    in
    0.88
    ف
    0.82
    <0x80>
    0.79
    f
    0.79
    ين
    0.77
    dır
    0.77
    на
    0.75
    ية
    0.75
     Magde
    0.73
    POSITIVE LOGITS
        
    0.74
       
    0.65
     debilitating
    0.65
     지원
    0.61
     screwing
    0.61
     עבור
    0.59
     wired
    0.58
     설정
    0.58
    蝌
    0.57
     丨
    0.57
    Activations Density 0.023%

    No Known Activations