© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80677
    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_0_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
     siis
    0.80
     یا
    0.74
     antara
    0.70
    <0x0D>
    0.67
     maju
    0.66
    is
    0.65
    एस
    0.63
     awal
    0.62
    <0xE3>
    0.62
    し
    0.61
    POSITIVE LOGITS
    ية
    0.65
    箖
    0.63
     ውሃ
    0.61
    ibilität
    0.61
    ách
    0.60
    ور
    0.59
    ní
    0.59
    νο
    0.58
     claridad
    0.58
    
    0.58
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.