© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27783
    Prev
    Next
    INDEX
    Explanations

    trick and tricking

    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_10_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
    "
    0.89
    is
    0.66
     you
    0.66
    ”
    0.63
     food
    0.62
    0
    0.61
     culinary
    0.61
     chef
    0.60
    না
    0.58
     the
    0.57
    POSITIVE LOGITS
    ك
    0.80
    s
    0.76
    دى
    0.70
    д
    0.68
     అంద
    0.67
     Tricks
    0.67
    ນ
    0.67
     tricked
    0.66
     Trick
    0.65
     بين
    0.64
    Activations Density 0.038%

    No Known Activations