© 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. 198446
    Prev
    Next
    INDEX
    Explanations

    diverse languages, meanings

    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
     apparently
    0.40
    how
    0.39
     unnoticed
    0.39
     from
    0.39
    /
    0.39
    日期
    0.39
    lying
    0.38
     необы
    0.38
     thro
    0.38
     dart
    0.38
    POSITIVE LOGITS
     المستوى
    0.40
    我看
    0.39
    ពេលវេល
    0.39
    冼
    0.38
    Desired
    0.38
    ລ
    0.38
    順
    0.37
    }}^{*}\
    0.37
    要求
    0.37
     تعالی
    0.37
    Activations Density 0.010%

    No Known Activations