© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57904
    Prev
    Next
    INDEX
    Explanations

    religion and spirituality

    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_11_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
    ǀ
    0.54
    峣
    0.54
    ರುತ್ತದೆ
    0.50
    UD
    0.48
    Ⅰ
    0.47
    Wei
    0.47
    Huang
    0.47
    Falls
    0.46
    রাগ
    0.46
    秭
    0.46
    POSITIVE LOGITS
    ant
    0.54
    пе
    0.54
    endedor
    0.52
    ers
    0.51
     perpendicularly
    0.49
    endez
    0.49
    тель
    0.48
     дре
    0.47
    \*
    0.47
     совершенно
    0.47
    Activations Density 0.021%

    No Known Activations