© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126060
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    کار
    0.89
    کل
    0.85
    ری
    0.83
    کن
    0.78
     It
    0.77
    س
    0.77
    شی
    0.75
     atvej
    0.73
    ید
    0.72
     invern
    0.72
    POSITIVE LOGITS
    r
    0.76
    ى
    0.70
    ر
    0.66
    ير
    0.66
     has
    0.62
    يد
    0.62
    IED
    0.61
    zaam
    0.60
    _+
    0.59
     is
    0.58
    Activations Density 0.000%

    No Known Activations