© 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. 206210
    Prev
    Next
    INDEX
    Explanations

    magic spells and curses

    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
    ląd
    0.43
     categorias
    0.39
     Aviv
    0.38
    uthers
    0.38
    糠
    0.37
     Palestina
    0.37
     electrodes
    0.37
     insult
    0.37
    Tron
    0.37
     propylene
    0.36
    POSITIVE LOGITS
    魔法
    1.20
     magical
    1.13
     magic
    1.04
     Magical
    1.00
     magicians
    0.99
    魔
    0.97
     magia
    0.95
     magie
    0.93
    Magic
    0.93
     जादू
    0.90
    Activations Density 0.001%

    No Known Activations