© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138154
    Prev
    Next
    INDEX
    Explanations

    Stack Overflow and Stack Exchange

    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
    ᱒
    0.64
    ्रिक
    0.62
    리오
    0.59
    ק
    0.57
     año
    0.57
    먀
    0.57
     characterise
    0.56
    オ
    0.56
    дных
    0.55
     reac
    0.54
    POSITIVE LOGITS
    t
    0.66
    isma
    0.54
    indle
    0.51
     Picking
    0.51
    g
    0.51
    adays
    0.50
    ate
    0.49
    nya
    0.48
    rs
    0.46
     Aunt
    0.46
    Activations Density 0.000%

    No Known Activations