© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 137204
    Prev
    Next
    INDEX
    Explanations

    mini golf

    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_37_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
    ंटो
    0.42
    ню
    0.38
    joint
    0.36
    鼈
    0.36
    cellular
    0.36
    Joint
    0.36
    沙
    0.36
    contract
    0.35
    指
    0.35
    sand
    0.34
    POSITIVE LOGITS
     mini
    0.88
     Mini
    0.79
     MINI
    0.78
    Mini
    0.75
     мини
    0.74
    ミニ
    0.73
    迷你
    0.73
     ミニ
    0.73
     minis
    0.72
    mini
    0.69
    Activations Density 0.001%

    No Known Activations