© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193790
    Prev
    Next
    INDEX
    Explanations

    numbers before "years", "children", or "similar"

    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_27_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
    两
    0.52
    这两
    0.46
    ه‌ای
    0.41
     שני
    0.41
    两天
    0.41
     两
    0.41
    这两个
    0.40
     اثنين
    0.39
     Recordemos
    0.39
    兩個
    0.38
    POSITIVE LOGITS
     warriors
    0.44
     seascape
    0.43
     motorcycle
    0.40
     uart
    0.40
    薬
    0.40
     prét
    0.38
     correspondance
    0.38
     DIO
    0.38
     soldiers
    0.38
     bike
    0.38
    Activations Density 0.003%

    No Known Activations