© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211073
    Prev
    Next
    INDEX
    Explanations

    endings of words

    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_5_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
    um
    0.80
    at
    0.70
    า
    0.64
    ie
    0.63
    ia
    0.63
    -
    0.60
    rs
    0.59
    на
    0.59
    ات
    0.57
    но
    0.57
    POSITIVE LOGITS
    一
    0.80
    д
    0.77
    {
    0.76
    د
    0.71
    ای
    0.69
    ()`
    0.68
    ‌ای
    0.68
    дные
    0.68
    )
    0.68
    ۶
    0.66
    Activations Density 0.000%

    No Known Activations