© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211840
    Prev
    Next
    INDEX
    Explanations

    escribe Russian

    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_5_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
     vives
    0.99
     provoqu
    0.96
    。
    0.96
    но
    0.93
     présentes
    0.93
    ت
    0.93
    dirs
    0.92
     ہوگی
    0.91
    مان
    0.88
    lines
    0.86
    POSITIVE LOGITS
     be
    1.37
    ный
    1.37
     is
    1.34
    ка
    1.32
    ский
    1.16
    ية
    1.12
    ים
    1.10
     an
    1.05
    q
    1.03
    ή
    1.03
    Activations Density 0.000%

    No Known Activations