© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12693
    Prev
    Next
    INDEX
    Explanations

    amusement park attractions

    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_13_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
    will
    0.58
    Moj
    0.57
    ومة
    0.56
    Room
    0.55
    s
    0.54
    Plan
    0.53
    In
    0.53
    다
    0.53
    ای
    0.52
    ee
    0.52
    POSITIVE LOGITS
    🎡
    0.71
    🎪
    0.59
    bbene
    0.55
    "%>
    0.55
     definiert
    0.54
     吃
    0.53
     ..."
    0.51
     把
    0.50
    ូប
    0.49
     sehingga
    0.49
    Activations Density 0.020%

    No Known Activations