© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221879
    Prev
    Next
    INDEX
    Explanations

    why it's

    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
     zelf
    0.58
    ็ม
    0.57
     객
    0.54
     그것
    0.53
     Đó
    0.51
     vissa
    0.49
    That
    0.49
     Enfin
    0.48
    AK
    0.47
     fera
    0.47
    POSITIVE LOGITS
    -
    0.57
    张
    0.56
    I
    0.54
    ढ़ाई
    0.51
    доб
    0.50
     chroma
    0.49
    是
    0.49
    t
    0.48
    à
    0.47
     décadas
    0.46
    Activations Density 0.016%

    No Known Activations