© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13984
    Prev
    Next
    INDEX
    Explanations

    fluctuations and maps

    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_15_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
    PVC
    0.52
     APC
    0.50
    Niger
    0.49
     PCBs
    0.49
    APC
    0.49
    ঝে
    0.48
    적
    0.47
     PMC
    0.47
     arrêt
    0.46
     Öz
    0.46
    POSITIVE LOGITS
     LIBRARY
    0.50
     рэгістра
    0.48
     způ
    0.48
    器材
    0.48
     مید
    0.46
    ⑴
    0.46
     сообщи
    0.46
     उपमुख्यमंत्री
    0.45
     باتوں
    0.45
    店铺
    0.45
    Activations Density 0.010%

    No Known Activations