© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4765
    Prev
    Next
    INDEX
    Explanations

    doctor appointments

    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_40_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
     статистики
    0.38
     Chemists
    0.37
    彧
    0.37
    δος
    0.37
     assistência
    0.37
    ٛ
    0.37
     அமைச்ச
    0.37
    /"+
    0.36
    dna
    0.36
    곽
    0.36
    POSITIVE LOGITS
     ordering
    0.93
     orders
    0.91
     Ordering
    0.86
    Ordering
    0.86
     Orders
    0.84
    ordering
    0.82
    สั่ง
    0.82
     ordered
    0.82
    Orders
    0.77
     order
    0.76
    Activations Density 0.091%

    No Known Activations