© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10185
    Prev
    Next
    INDEX
    Explanations

    UHD Graphics, built-in

    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_13_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
     употре
    0.59
     у
    0.49
    पर्या
    0.47
     изда
    0.44
     о
    0.44
    दि
    0.43
     да
    0.43
    ۇل
    0.43
     važ
    0.42
     уз
    0.42
    POSITIVE LOGITS
     lọc
    0.46
    ե
    0.45
    ಮೀ
    0.44
     sisi
    0.41
     فناوری
    0.41
    нков
    0.40
    ToEnd
    0.40
    Aggregation
    0.39
    orsement
    0.39
    Weights
    0.39
    Activations Density 0.087%

    No Known Activations