© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17955
    Prev
    Next
    INDEX
    Explanations

    Eagle

    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_15_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
    loading
    0.55
    icios
    0.44
    load
    0.44
    "];
    0.43
    coma
    0.43
     mua
    0.42
    espresso
    0.42
     नंबर
    0.42
    лся
    0.42
    icle
    0.41
    POSITIVE LOGITS
     Франции
    0.47
    黴
    0.46
     Gottfried
    0.44
     ወቅ
    0.44
    WCHAR
    0.43
     삼각형
    0.43
    ющем
    0.43
     গভর্ন
    0.42
     fortiter
    0.42
     plates
    0.41
    Activations Density 0.001%

    No Known Activations