© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44937
    Prev
    Next
    INDEX
    Explanations

    procedures and procs

    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
    ط
    0.95
    는
    0.88
    ла
    0.86
    ला
    0.82
    ため
    0.80
    ad
    0.77
    am
    0.77
    ب
    0.77
    ನ
    0.76
    தி
    0.74
    POSITIVE LOGITS
     proc
    0.98
     I
    0.98
     for
    0.96
    I
    0.93
     procura
    0.83
     have
    0.82
     a
    0.81
     A
    0.79
     E
    0.79
     procedures
    0.78
    Activations Density 0.013%

    No Known Activations