© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33513
    Prev
    Next
    INDEX
    Explanations

    class Dog definitions with breed

    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_31_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
     বাঙ্গাল
    0.34
     insulating
    0.33
    engl
    0.32
     insulation
    0.32
     insulator
    0.30
     insulate
    0.30
    structural
    0.29
    苾
    0.29
    过滤
    0.29
     structural
    0.29
    POSITIVE LOGITS
     Animals
    0.42
     animals
    0.42
     동물
    0.41
     animal
    0.41
     animales
    0.41
    Animals
    0.39
    สัตว์
    0.39
     dogs
    0.38
     एनिमल
    0.38
     собаки
    0.37
    Activations Density 0.007%

    No Known Activations