© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43007
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun endings

    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_22_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
    WR
    0.41
    від
    0.39
    typen
    0.39
    URUK
    0.38
    Ｒ
    0.38
    UNICATIONS
    0.38
    self
    0.37
    protractor
    0.37
    ដ្ឋាន
    0.37
    결
    0.37
    POSITIVE LOGITS
     Mobile
    0.44
     teléfono
    0.42
     provoquer
    0.40
     insufficiently
    0.40
     MOBILE
    0.39
    龚
    0.39
     théorème
    0.39
     delay
    0.38
    ную
    0.38
    madı
    0.38
    Activations Density 0.002%

    No Known Activations