© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 212209
    Prev
    Next
    INDEX
    Explanations

    axis

    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_43_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
     बैन
    0.41
    page
    0.40
    ्या
    0.39
    页面
    0.38
     멋
    0.38
     strán
    0.37
     страница
    0.37
     বোর্ড
    0.37
     страницу
    0.37
    LoginPage
    0.35
    POSITIVE LOGITS
    সমূ
    0.42
    쎌
    0.41
    適
    0.40
    agama
    0.39
     PubMed
    0.39
    ށް
    0.39
    샹
    0.39
     pem
    0.38
     PPM
    0.38
     ppm
    0.37
    Activations Density 0.002%

    No Known Activations