© 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. 35081
    Prev
    Next
    INDEX
    Explanations

    government buildings and employees

    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
    يد
    0.68
     entw
    0.66
     besch
    0.63
    喵
    0.62
     modell
    0.61
     descrito
    0.60
    0.60
     I
    0.59
     grotes
    0.59
    ى
    0.59
    POSITIVE LOGITS
    یت
    0.88
    ری
    0.85
    ction
    0.77
    لی
    0.77
    加え
    0.77
    کنندگان
    0.76
    یک
    0.74
    \}=
    0.71
    ‌ای
    0.71
    てください
    0.70
    Activations Density 0.002%

    No Known Activations