© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206927
    Prev
    Next
    INDEX
    Explanations

    religious leaders and institutions

    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_10_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
    임
    0.44
    ンダ
    0.44
    ング
    0.39
    ﺩ
    0.39
    authorized
    0.38
    ром
    0.37
    applications
    0.37
    ،
    0.37
    лле
    0.36
     maneras
    0.36
    POSITIVE LOGITS
    isesti
    0.46
    kirche
    0.45
     Jedi
    0.45
     v
    0.45
     vous
    0.44
     igreja
    0.44
    精灵
    0.44
     அற்புத
    0.43
     Ghost
    0.43
    éssel
    0.43
    Activations Density 0.010%

    No Known Activations