© 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. 45110
    Prev
    Next
    INDEX
    Explanations

    wool

    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
    -
    0.91
    ı
    0.77
    ا
    0.76
     (
    0.75
    AH
    0.75
    ap
    0.71
    గా
    0.71
    é
    0.70
    B
    0.70
    ما
    0.70
    POSITIVE LOGITS
     писать
    0.67
    த்ரே
    0.65
     لیګ
    0.65
    ین
    0.64
    inę
    0.63
    வ்வேறு
    0.62
    ется
    0.62
     TRANSPORTURI
    0.61
     inactivació
    0.61
     від
    0.61
    Activations Density 0.003%

    No Known Activations