© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157859
    Prev
    Next
    INDEX
    Explanations

    landowners and land use

    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_2_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
    د
    2.28
    ف
    1.96
    д
    1.93
    ج
    1.82
    ح
    1.74
    ك
    1.64
    س
    1.52
    ある
    1.52
    ت
    1.52
    ق
    1.48
    POSITIVE LOGITS
    s
    1.17
     in
    1.13
    IS
    1.02
     by
    1.01
     lê
    1.00
    Jn
    0.99
    X
    0.99
     musica
    0.94
     vulture
    0.91
     rédaction
    0.90
    Activations Density 0.000%

    No Known Activations