© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10884
    Prev
    Next
    INDEX
    Explanations

    you tell

    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
     It
    0.55
    Whenever
    0.49
    artner
    0.48
    Date
    0.46
     pono
    0.46
    бов
    0.46
    Loc
    0.46
    ब
    0.44
    It
    0.44
     드
    0.43
    POSITIVE LOGITS
    তাহাকে
    0.54
     приводит
    0.51
     fudai
    0.49
     orphanage
    0.49
     Tokugawa
    0.48
     ඔහුගේ
    0.48
     основной
    0.48
    കൊണ്ട്
    0.47
     jurisprudence
    0.47
     ontological
    0.47
    Activations Density 0.005%

    No Known Activations