© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131662
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
     Szcz
    0.98
     Otros
    0.94
     Sereth
    0.93
    ⒏
    0.91
     Varan
    0.90
    to
    0.89
     Ghent
    0.89
     hermosa
    0.89
     Jaaye
    0.89
     Kita
    0.88
    POSITIVE LOGITS
    는
    1.11
    是
    0.98
    ۔
    0.98
    ة
    0.93
    한
    0.89
    ی
    0.88
    ان
    0.86
    ال
    0.84
     ionized
    0.84
    มัน
    0.82
    Activations Density 0.000%

    No Known Activations