© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226273
    Prev
    Next
    INDEX
    Explanations

    ```csharpclass Controller

    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_10_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
    6
    0.71
     the
    0.70
    1
    0.65
     to
    0.64
     ayant
    0.62
    2
    0.61
    Count
    0.61
    ,
    0.60
     arrondi
    0.59
    Data
    0.59
    POSITIVE LOGITS
    ۔
    0.58
    vä
    0.58
    amm
    0.55
    ро
    0.55
    ológ
    0.55
    <0x85>
    0.54
     এক
    0.54
    <0x9D>
    0.53
    ര്‍
    0.51
    monium
    0.50
    Activations Density 0.001%

    No Known Activations