© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159677
    Prev
    Next
    INDEX
    Explanations

    virtual worlds

    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_2_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
    in
    1.05
    i
    0.88
    ja
    0.83
    it
    0.81
    n
    0.80
    to
    0.78
    the
    0.77
    o
    0.76
    ze
    0.75
    ft
    0.72
    POSITIVE LOGITS
     as
    1.16
    리
    0.94
    ુ
    0.91
    ट
    0.89
     quais
    0.88
    ص
    0.88
    ก
    0.83
    ется
    0.81
    ари
    0.79
    って
    0.78
    Activations Density 0.001%

    No Known Activations