© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205239
    Prev
    Next
    INDEX
    Explanations

    bijections

    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_6_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
    l
    0.88
    h
    0.88
    M
    0.87
    g
    0.79
    j
    0.75
    x
    0.73
    K
    0.73
    d
    0.73
    re
    0.72
    t
    0.72
    POSITIVE LOGITS
    ות
    0.97
    ம்
    0.74
     refraction
    0.66
    ین
    0.64
    iato
    0.62
    ма
    0.61
    ্বেও
    0.61
    ವಾಗಿ
    0.60
     covariance
    0.60
    й
    0.59
    Activations Density 0.001%

    No Known Activations