© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61065
    Prev
    Next
    INDEX
    Explanations

    Scottsdale, Beach

    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_11_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
     Mulder
    0.71
     Estamos
    0.64
    ın
    0.62
     Gradle
    0.62
     Iod
    0.61
    <unused1821>
    0.61
    žka
    0.60
     سایټ
    0.59
     Seward
    0.59
    .`);
    0.59
    POSITIVE LOGITS
    ያንዳ
    0.57
    import
    0.55
    را
    0.53
    （
    0.52
    將
    0.52
    马
    0.51
    나
    0.49
     import
    0.48
    为
    0.48
    ニング
    0.47
    Activations Density 0.000%

    No Known Activations