© 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. 93518
    Prev
    Next
    INDEX
    Explanations

    adherence to rules or norms

    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
    ו
    0.64
    وو
    0.61
     use
    0.60
     notebook
    0.59
    <0x80>
    0.58
    ொள்ள
    0.57
    η
    0.57
     roaring
    0.56
    <0x86>
    0.56
     champ
    0.56
    POSITIVE LOGITS
    ampur
    0.65
    3
    0.64
    amak
    0.64
    ayat
    0.63
    års
    0.63
    ancers
    0.62
    ar
    0.61
    mek
    0.59
    ajte
    0.59
    escens
    0.59
    Activations Density 0.002%

    No Known Activations