© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88537
    Prev
    Next
    INDEX
    Explanations

    GLSL code includes position

    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
    ים
    0.70
    (
    0.64
    ्स
    0.63
    -$\
    0.62
    <0x0D>
    0.62
    ン
    0.60
    配色
    0.59
    ーカー
    0.58
     echoed
    0.58
     ImageIcon
    0.58
    POSITIVE LOGITS
    ना
    0.73
     dezvolt
    0.65
     fraudulently
    0.57
     chữa
    0.56
    ቀ
    0.55
    値
    0.55
     turquoise
    0.54
    cott
    0.54
    0.53
     doméstica
    0.52
    Activations Density 0.001%

    No Known Activations