© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89664
    Prev
    Next
    INDEX
    Explanations

    arm's length

    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_11_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
    window
    0.63
    map
    0.60
    ven
    0.60
    tti
    0.60
    स
    0.60
    garden
    0.57
    mimpi
    0.57
    tch
    0.55
    ):
    0.55
    wallpaper
    0.55
    POSITIVE LOGITS
     ferrugineux
    0.60
    但在
    0.59
    ى
    0.57
    烦
    0.56
     pieno
    0.55
     αλλά
    0.52
    နိုင်
    0.51
    َة
    0.51
     giàu
    0.51
    钻
    0.51
    Activations Density 0.000%

    No Known Activations