© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43629
    Prev
    Next
    INDEX
    Explanations

    spanish definite articles

    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_13_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
     t
    0.71
     structures
    0.59
     A
    0.56
     ch
    0.56
    T
    0.55
     car
    0.54
     unem
    0.54
     T
    0.53
     purs
    0.53
     wre
    0.53
    POSITIVE LOGITS
    furniture
    0.61
    dimethyl
    0.61
    which
    0.60
    ozone
    0.60
    business
    0.59
    pleasant
    0.58
    protein
    0.58
    ylim
    0.58
    andingan
    0.58
    apartment
    0.58
    Activations Density 0.015%

    No Known Activations