© 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. 32941
    Prev
    Next
    INDEX
    Explanations

    further

    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
     hacia
    0.46
     toward
    0.44
    向
    0.39
    towards
    0.38
     Toward
    0.37
    Toward
    0.37
     towards
    0.37
    學
    0.36
    Pope
    0.35
     學
    0.35
    POSITIVE LOGITS
     off
    0.40
    agel
    0.40
    логу
    0.39
     දී
    0.39
     ဗ
    0.38
    لود
    0.38
     PE
    0.38
     Loi
    0.37
    ygons
    0.37
    aged
    0.37
    Activations Density 0.002%

    No Known Activations