© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156876
    Prev
    Next
    INDEX
    Explanations

    wind speed and direction

    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_2_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
     \
    1.13
     for
    0.98
     woord
    0.89
     Mét
    0.88
     $\
    0.86
     gewoon
    0.85
     vraag
    0.82
    ле
    0.81
     دين
    0.81
     تصميم
    0.80
    POSITIVE LOGITS
    ك
    1.97
    ل
    1.59
    し
    1.53
    ка
    1.46
    ان
    1.45
    ના
    1.40
    یت
    1.40
    the
    1.34
    های
    1.31
    ul
    1.24
    Activations Density 0.001%

    No Known Activations