© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86001
    Prev
    Next
    INDEX
    Explanations

    Water Conservation

    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_3_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
    ו
    0.91
    و
    0.91
    ی
    0.79
    и
    0.75
    ה
    0.71
    stargo
    0.65
    т
    0.65
    ا
    0.64
    ари
    0.63
    ки
    0.61
    POSITIVE LOGITS
    ’
    0.78
    ía
    0.70
    …’
    0.63
    '
    0.63
    ur
    0.62
    ,’
    0.62
    ak
    0.61
    ón
    0.60
    ികിത്സ
    0.60
     वजह
    0.60
    Activations Density 0.001%

    No Known Activations