© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32865
    Prev
    Next
    INDEX
    Explanations

    logic programming rules

    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_31_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
    鍚
    0.39
     meaningless
    0.37
     одно
    0.37
    報酬
    0.35
     ग्राहक
    0.35
     வகு
    0.35
     blem
    0.35
    ຕໍ່
    0.35
     senseless
    0.34
     закры
    0.34
    POSITIVE LOGITS
    🏾
    0.40
    protos
    0.36
    Yep
    0.36
     Viitattu
    0.36
     Боль
    0.35
    Spirit
    0.35
    Vere
    0.35
     Heap
    0.35
    MTV
    0.35
     corresponds
    0.34
    Activations Density 0.000%

    No Known Activations