© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139618
    Prev
    Next
    INDEX
    Explanations

    dragons

    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
    gete
    0.38
     VESSELS
    0.37
     bastard
    0.36
    stroke
    0.36
    walle
    0.35
    ೋಟ
    0.35
    DomainMask
    0.35
    荐
    0.35
    bitmap
    0.35
     strokes
    0.35
    POSITIVE LOGITS
     dragon
    1.14
     dragons
    1.08
     Dragon
    1.02
     Dragons
    0.96
    Dragon
    0.94
    龙
    0.92
    🐉
    0.91
    🐲
    0.89
    龍
    0.86
    dragon
    0.83
    Activations Density 0.052%

    No Known Activations