© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206366
    Prev
    Next
    INDEX
    Explanations

    I'll break down

    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_6_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
    ر
    1.09
    ли
    1.03
    اين
    1.03
     جاي
    0.98
     forgo
    0.95
    ту
    0.93
     CaCl
    0.88
    ógrafo
    0.88
     Badajoz
    0.88
     Flughafen
    0.88
    POSITIVE LOGITS
    ik
    0.90
    ור
    0.89
    :
    0.86
    mber
    0.83
    ları
    0.81
    ี
    0.81
    matic
    0.80
    1
    0.78
    ¹
    0.78
    hed
    0.77
    Activations Density 0.011%

    No Known Activations