© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 89345
    Prev
    Next
    INDEX
    Explanations

    restrictions, features, subset, profiles

    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_18_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
    िक
    0.45
    える
    0.43
    czyć
    0.42
    ě
    0.41
    iale
    0.40
    <0x83>
    0.40
    antly
    0.40
     leveling
    0.39
    ruik
    0.39
     supl
    0.38
    POSITIVE LOGITS
    ผ่าน
    0.57
    Breakfast
    0.52
    Airbnb
    0.52
     பயன்ப
    0.50
     प्रतिबंधित
    0.49
     "????.??.??"]
    0.49
    Through
    0.49
    விட்டால்
    0.49
    ⼈
    0.49
     அதி
    0.48
    Activations Density 0.010%

    No Known Activations