© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 152659
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    long
    0.66
    LONG
    0.61
     long
    0.60
     longa
    0.60
    长的
    0.58
    长
    0.58
     longue
    0.58
     طويلة
    0.57
    長
    0.56
     дъл
    0.56
    POSITIVE LOGITS
     mid
    0.54
     if
    0.48
     Mid
    0.46
    Mid
    0.46
     layer
    0.45
     если
    0.44
     sphere
    0.43
     area
    0.42
     region
    0.42
     fraction
    0.42
    Activations Density 0.002%

    No Known Activations