© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51031
    Prev
    Next
    INDEX
    Explanations

    computation analysis simulation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    距離
    0.38
     kaug
    0.38
     العمود
    0.37
    """"""""
    0.37
    pragma
    0.37
     ক্যামের
    0.36
    uele
    0.36
    땔
    0.36
     rhetoric
    0.35
    棿
    0.35
    POSITIVE LOGITS
     numerical
    0.57
    Computational
    0.55
     Finite
    0.55
     computational
    0.54
     Computational
    0.54
    Numerical
    0.54
    Finite
    0.54
     Numerical
    0.52
     finite
    0.52
     числен
    0.48
    Activations Density 0.007%

    No Known Activations