© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90354
    Prev
    Next
    INDEX
    Explanations

    Holy Roman Empire

    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_3_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
    
    0.69
    
    0.68
     оно
    0.68
    ᱴ
    0.68
     Володи
    0.66
    ꯋ
    0.64
    寯
    0.64
    STRING
    0.64
     කොට
    0.62
     Максим
    0.62
    POSITIVE LOGITS
    m
    0.97
     of
    0.94
     is
    0.89
    p
    0.82
    us
    0.82
    ست
    0.77
    b
    0.76
     has
    0.74
    ट
    0.73
     faktisk
    0.70
    Activations Density 0.000%

    No Known Activations