© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155404
    Prev
    Next
    INDEX
    Explanations

    position

    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
     over
    0.50
     ওভার
    0.44
    loadNpmTasks
    0.42
    过
    0.42
     Over
    0.42
    オーバー
    0.41
    Over
    0.41
     över
    0.40
    orso
    0.40
     ओवर
    0.40
    POSITIVE LOGITS
    愪
    0.41
     открыть
    0.38
     теку
    0.37
    ඈ
    0.37
    illow
    0.37
    催
    0.37
    屈
    0.36
    piar
    0.35
    sigma
    0.35
    центри
    0.35
    Activations Density 0.003%

    No Known Activations