© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142367
    Prev
    Next
    INDEX
    Explanations

    formulating arguments, plans, or policies

    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_0_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
    ع
    2.08
    س
    1.91
    ق
    1.73
    ا
    1.66
    the
    1.66
    v
    1.66
    ف
    1.66
    на
    1.62
    ні
    1.58
    д
    1.57
    POSITIVE LOGITS
     t
    1.43
     for
    1.43
     in
    1.42
    inin
    1.23
     d
    1.22
     dressed
    1.20
    ℡
    1.19
     b
    1.18
    ﺍ
    1.18
    ﯼ
    1.18
    Activations Density 0.001%

    No Known Activations