© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131788
    Prev
    Next
    INDEX
    Explanations

    pattern recognition

    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_6_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
    ק
    1.28
    स
    1.14
    f
    1.11
    ка
    0.99
    ك
    0.95
    اد
    0.93
    ق
    0.93
    س
    0.92
    פ
    0.87
    স
    0.83
    POSITIVE LOGITS
    ról
    1.09
     ricerca
    0.89
     danza
    0.89
     tecnologia
    0.89
     tân
    0.87
     domanda
    0.87
     diaria
    0.86
     lembra
    0.86
     branca
    0.84
     consegna
    0.84
    Activations Density 0.008%

    No Known Activations