© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47413
    Prev
    Next
    INDEX
    Explanations

    online services and platforms

    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_10_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
    ために
    0.77
    M
    0.73
    K
    0.73
    5
    0.67
    D
    0.66
     novelist
    0.63
     在
    0.63
    F
    0.62
     mã
    0.61
    W
    0.59
    POSITIVE LOGITS
    of
    0.75
    ূতন
    0.74
    ."]
    0.71
    чки
    0.70
    כם
    0.68
    ем
    0.65
    ISION
    0.64
    раль
    0.64
    তৃত
    0.63
    ār
    0.63
    Activations Density 0.005%

    No Known Activations