© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88048
    Prev
    Next
    INDEX
    Explanations

    James Thompson Morrison

    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_3_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
    E
    0.61
     яко
    0.57
    ۹
    0.57
    U
    0.56
    T
    0.55
    zee
    0.51
    isn
    0.51
    еры
    0.51
     pobres
    0.51
    mobility
    0.51
    POSITIVE LOGITS
    дт
    0.65
    o
    0.64
    לה
    0.62
    ية
    0.61
    ל
    0.60
    ם
    0.59
    ำ
    0.59
    2
    0.57
    参
    0.57
    功夫
    0.55
    Activations Density 0.002%

    No Known Activations