© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41933
    Prev
    Next
    INDEX
    Explanations

    built environment

    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
    AN
    0.91
    {
    0.80
    ant
    0.78
    G
    0.75
    K
    0.73
    D
    0.71
    লে
    0.69
     bullets
    0.69
     намере
    0.67
    ak
    0.65
    POSITIVE LOGITS
    dengan
    0.73
     oposición
    0.66
    ウム
    0.64
    成
    0.63
    projeto
    0.62
    fluss
    0.61
    事情
    0.61
    kod
    0.61
    bentuk
    0.61
    vý
    0.61
    Activations Density 0.024%

    No Known Activations