© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198413
    Prev
    Next
    INDEX
    Explanations

    laws and codes

    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_15_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
    스포츠
    0.56
    स्क्रीन
    0.55
    Critics
    0.54
     دی
    0.53
    デ
    0.53
     उल्लेखनीय
    0.53
    ловек
    0.50
     Escobar
    0.50
    ދ
    0.49
     Island
    0.49
    POSITIVE LOGITS
    ните
    0.49
    ною
    0.49
     bantuan
    0.48
     recombinant
    0.48
    ாதார
    0.48
    нет
    0.47
    ڃ
    0.47
     need
    0.46
     face
    0.46
    ıklı
    0.46
    Activations Density 0.000%

    No Known Activations