© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231860
    Prev
    Next
    INDEX
    Explanations

    numbers and currency symbols

    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_6_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
    ।
    1.42
    the
    1.14
    ۔
    1.09
    ຜະລິດຕະພັນ
    0.93
    an
    0.88
    ta
    0.88
     the
    0.87
    t
    0.86
    ர்
    0.86
    li
    0.85
    POSITIVE LOGITS
    会
    0.94
     přímo
    0.83
     mají
    0.82
     egyszerű
    0.81
     přest
    0.76
    的
    0.75
     ngày
    0.75
    潜在
    0.75
    可以
    0.74
    బ్ద
    0.74
    Activations Density 0.003%

    No Known Activations