© 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. 121442
    Prev
    Next
    INDEX
    Explanations

    magical spells and actions

    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
    糠
    0.46
     Omega
    0.39
    aturated
    0.37
    Omega
    0.37
    olithic
    0.37
     buty
    0.37
    uthers
    0.36
    ሸ
    0.35
     kHz
    0.35
    কতা
    0.35
    POSITIVE LOGITS
     magical
    1.45
    魔法
    1.42
     magic
    1.27
     spell
    1.24
     spells
    1.23
     Magical
    1.17
     magically
    1.16
     magia
    1.15
     mágico
    1.13
     маги
    1.11
    Activations Density 0.096%

    No Known Activations