© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150823
    Prev
    Next
    INDEX
    Explanations

    square kilometers or miles

    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_23_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
     Sy
    0.42
    detalle
    0.42
     elucidation
    0.41
     Rights
    0.40
     Thermodynamic
    0.39
     suggesting
    0.39
    罍
    0.39
     Toner
    0.39
     Disputes
    0.39
     Baker
    0.38
    POSITIVE LOGITS
     mädchen
    0.40
     mình
    0.39
    skyblue
    0.38
     stabilized
    0.38
     feb
    0.38
    ürn
    0.38
    ἢ
    0.38
     veterin
    0.37
     poesia
    0.37
     프로젝트
    0.37
    Activations Density 0.000%

    No Known Activations