© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157018
    Prev
    Next
    INDEX
    Explanations

    verb past and present participles

    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_2_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
    _
    0.86
    ation
    0.85
    is
    0.81
    الم
    0.81
    C
    0.79
    ли
    0.75
    ized
    0.75
    其他
    0.75
    个
    0.74
    p
    0.71
    POSITIVE LOGITS
    ्स
    0.87
    ו
    0.71
    ,
    0.63
    ים
    0.61
     affixed
    0.60
     burdened
    0.60
    )\}
    0.59
     adjudged
    0.58
    ्सा
    0.57
    dı
    0.57
    Activations Density 0.002%

    No Known Activations