© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9189
    Prev
    Next
    INDEX
    Explanations

    fortified cities and defenses

    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_13_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
    鹕
    0.57
     Möbius
    0.53
     ধাক
    0.52
    導數
    0.52
     Intensive
    0.51
     molécule
    0.51
    왁
    0.51
    ่า
    0.50
     Piaget
    0.50
    aw
    0.50
    POSITIVE LOGITS
    Castle
    0.55
    笆
    0.54
     castle
    0.50
    {
    0.50
    Lov
    0.49
     defence
    0.48
     سجل
    0.48
    ון
    0.48
    SPACE
    0.48
    LINE
    0.47
    Activations Density 0.021%

    No Known Activations