© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24445
    Prev
    Next
    INDEX
    Explanations

    diverse topics or languages

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     раз
    2.53
     raz
    2.22
     roz
    1.76
    Raz
    1.75
     Raz
    1.73
     forsk
    1.66
     versch
    1.62
    分
    1.59
    raz
    1.54
    раз
    1.49
    POSITIVE LOGITS
    ่าง
    0.50
    ຕ
    0.50
    ່າງ
    0.43
    ต่
    0.43
    ">{{
    0.38
     వే
    0.37
    interrupt
    0.37
     ଭ
    0.37
     భ
    0.36
    Ди
    0.36
    Activations Density 0.013%

    No Known Activations