© 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. 137819
    Prev
    Next
    INDEX
    Explanations

    tractors

    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
     farmer
    0.55
     pos
    0.54
     ס
    0.52
    ↵
    0.52
    Farmer
    0.51
     Apple
    0.51
     Farmer
    0.51
     tractors
    0.50
     Tractor
    0.50
    Farmers
    0.50
    POSITIVE LOGITS
    aság
    0.60
    ⵎ
    0.59
    itecture
    0.50
    ).\
    0.49
     কোথায়
    0.49
    algorith
    0.48
    锛
    0.48
     алгорит
    0.47
    dyna
    0.47
    œuf
    0.47
    Activations Density 0.000%

    No Known Activations