© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33642
    Prev
    Next
    INDEX
    Explanations

    PB, FreePBX, FreeRTOS, cancellation

    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_3_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
    ные
    0.69
    ра
    0.66
    ņu
    0.66
    NUS
    0.64
    ный
    0.63
    的
    0.63
    ли
    0.61
    nya
    0.61
    sman
    0.61
    ਤ
    0.61
    POSITIVE LOGITS
     for
    0.96
     घ
    0.69
    ér
    0.64
     पाँच
    0.59
     generalization
    0.59
     alleviating
    0.58
     eliminating
    0.57
     equivoc
    0.57
     рів
    0.56
     originality
    0.56
    Activations Density 0.002%

    No Known Activations