© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57934
    Prev
    Next
    INDEX
    Explanations

    function, spider, tired, fatigued, abilities

    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_11_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
     Einführung
    0.54
     Duque
    0.52
    Má
    0.52
    0
    0.52
    (|
    0.51
     الآخر
    0.50
    住宿
    0.49
    其他
    0.48
    电脑
    0.48
    يل
    0.46
    POSITIVE LOGITS
     blur
    0.54
     ก
    0.52
     นาย
    0.51
     blurry
    0.49
     staring
    0.46
     midnight
    0.46
     ที่
    0.46
    که
    0.46
     forgetting
    0.46
     biodegradable
    0.46
    Activations Density 0.000%

    No Known Activations