© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177513
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     mandrel
    0.42
    <0x8E>
    0.40
     instituciones
    0.39
    杏
    0.38
     Homeland
    0.38
     পাঁ
    0.38
     raisin
    0.38
    рей
    0.38
    ں
    0.38
    ╱
    0.38
    POSITIVE LOGITS
     በላይ
    0.42
     wiggle
    0.37
    拝
    0.37
     Chr
    0.36
    ဗ
    0.36
     Vou
    0.35
    πε
    0.35
    भग
    0.34
    ிகை
    0.34
    epine
    0.34
    Activations Density 0.000%

    No Known Activations