© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125128
    Prev
    Next
    INDEX
    Explanations

    Brownfield, Seaweed, Motion, Derby

    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
     a
    0.82
     don
    0.75
     tomó
    0.68
     eup
    0.65
     aren
    0.64
    ა
    0.63
     da
    0.63
     afili
    0.63
     Java
    0.62
     miał
    0.61
    POSITIVE LOGITS
    ка
    0.98
    و
    0.76
    ك
    0.70
    ست
    0.63
     Heterocycl
    0.63
    小
    0.61
    其他
    0.61
    to
    0.61
    ки
    0.61
    не
    0.59
    Activations Density 0.000%

    No Known Activations