© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54288
    Prev
    Next
    INDEX
    Explanations

    next to assignment

    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_30_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
    ')",
    0.36
     meningkatkan
    0.35
     محسوس
    0.35
    先生
    0.34
     Superman
    0.34
    ')+
    0.34
    ारे
    0.34
    召唤
    0.34
     भौगोलिक
    0.34
     ingu
    0.34
    POSITIVE LOGITS
    衍
    0.39
     Шрифт
    0.39
     Otros
    0.37
     interrupted
    0.37
     шрифт
    0.36
    जन्
    0.35
     těchto
    0.35
     Others
    0.34
    也非常
    0.34
     innych
    0.34
    Activations Density 0.001%

    No Known Activations