© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90212
    Prev
    Next
    INDEX
    Explanations

    active pharmaceutical ingredient, play, light, seeking

    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_3_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
    3
    0.76
    지
    0.68
    ات
    0.68
    EN
    0.67
    AN
    0.64
    AT
    0.62
    AIN
    0.60
    ку
    0.60
    ogical
    0.59
    灿
    0.57
    POSITIVE LOGITS
     }}=\
    0.66
    w
    0.64
     eliminado
    0.63
    らは
    0.62
     таксама
    0.62
     гра
    0.61
     remplacement
    0.60
    อย่า
    0.59
    también
    0.59
    อัล
    0.58
    Activations Density 0.002%

    No Known Activations