© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 151249
    Prev
    Next
    INDEX
    Explanations

    divisible by 5

    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_18_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
    ඪ
    0.55
    ض
    0.53
    IRQHandler
    0.46
     Toán
    0.45
    ಟ
    0.45
    চাল
    0.44
    Increase
    0.44
    钙
    0.44
    یط
    0.44
    DOCT
    0.43
    POSITIVE LOGITS
     halogen
    0.55
     Outer
    0.52
     XX
    0.49
     sexy
    0.49
     UNS
    0.49
     Wür
    0.47
     BSD
    0.47
     tradition
    0.46
     Warna
    0.46
     Aren
    0.46
    Activations Density 0.003%

    No Known Activations