© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200261
    Prev
    Next
    INDEX
    Explanations

    Cape, Cape Town, Mountain

    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
    粘贴
    0.57
     leukocytes
    0.57
    ９
    0.57
    ERS
    0.56
    ные
    0.54
     Merced
    0.54
     الذين
    0.53
    གས་
    0.53
     harán
    0.53
    9
    0.53
    POSITIVE LOGITS
    Reasoner
    0.52
    discover
    0.48
     discovery
    0.48
     bespoke
    0.46
    abolic
    0.45
     flavour
    0.45
     Thorough
    0.44
    сторон
    0.44
     Swo
    0.44
     Dét
    0.44
    Activations Density 0.000%

    No Known Activations