© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140255
    Prev
    Next
    INDEX
    Explanations

    dates in mm/dd/yyyy format

    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_12_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
    д
    0.79
    ນິກ
    0.75
     Mississauga
    0.74
    дзен
    0.73
    νες
    0.71
    ൺ
    0.71
    onske
    0.71
    favourites
    0.69
    躇
    0.69
     Consultado
    0.68
    POSITIVE LOGITS
    ier
    0.62
    3
    0.61
    ंटर
    0.58
     naturalist
    0.57
     get
    0.56
    는
    0.54
     monumental
    0.53
     world
    0.51
     cran
    0.51
     tig
    0.49
    Activations Density 0.001%

    No Known Activations