© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158142
    Prev
    Next
    INDEX
    Explanations

    politics

    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_50_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
    Ra
    0.46
     Guil
    0.44
     Ra
    0.43
     G
    0.39
     organ
    0.38
     органи
    0.38
     raf
    0.38
    噹
    0.38
     органы
    0.38
    Ри
    0.37
    POSITIVE LOGITS
    缟
    0.44
     tulips
    0.41
    ullie
    0.41
     anch
    0.39
     අනුව
    0.39
     Insc
    0.39
     পরিত্র
    0.38
    ጄ
    0.38
     Projects
    0.38
    olve
    0.37
    Activations Density 0.000%

    No Known Activations