© 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. 133266
    Prev
    Next
    INDEX
    Explanations

    zirconicomputingpolicies

    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_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
     Noch
    0.95
    ↵
    0.93
    šao
    0.93
     Graduate
    0.84
    ك
    0.83
     National
    0.83
     Chu
    0.82
     ప్రమా
    0.82
     Changer
    0.82
    ן
    0.82
    POSITIVE LOGITS
    ۰
    0.96
     décrites
    0.95
    ین
    0.94
    ᱐
    0.90
     térm
    0.89
     biologiques
    0.88
    िंग
    0.88
    もり
    0.88
     traer
    0.86
    یک
    0.86
    Activations Density 0.000%

    No Known Activations