© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137619
    Prev
    Next
    INDEX
    Explanations

    classical poetry forms and structures

    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_12_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
     धरती
    0.49
     voice
    0.48
    recording
    0.47
     বিষয়
    0.47
    ️
    0.47
     recordings
    0.47
    影片
    0.47
    声音
    0.46
     می‌کنند
    0.46
    life
    0.44
    POSITIVE LOGITS
    ма
    0.55
    ные
    0.55
    )(=
    0.55
    пси
    0.54
    ز
    0.53
    ток
    0.51
    ку
    0.50
    ных
    0.49
    ца
    0.49
    to
    0.48
    Activations Density 0.000%

    No Known Activations