© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40885
    Prev
    Next
    INDEX
    Explanations

    rock and metal bands and genres

    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_11_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
     piatto
    0.58
    Geschichte
    0.56
    kan
    0.52
    逺
    0.52
     искусства
    0.51
     искусство
    0.49
     chirality
    0.49
    큥
    0.48
     இசை
    0.48
     плоско
    0.48
    POSITIVE LOGITS
     Telem
    0.70
    +
    0.67
     +
    0.63
    us
    0.59
    া
    0.57
     Nuts
    0.57
     terminer
    0.55
    ur
    0.55
     Honduras
    0.55
     Teles
    0.54
    Activations Density 0.003%

    No Known Activations