© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27163
    Prev
    Next
    INDEX
    Explanations

    waddled, trudged, or trotted

    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
    ্রো
    0.87
     गर्नु
    0.87
     會
    0.83
     on
    0.83
     ロ
    0.82
     WITH
    0.81
     紙
    0.80
     رو
    0.80
     واحد
    0.79
    álisis
    0.79
    POSITIVE LOGITS
    ز
    0.86
    ir
    0.78
    };
    0.70
    мени
    0.70
    ית
    0.68
    ol
    0.67
    nya
    0.67
    ).
    0.66
    ;
    0.64
    ებაში
    0.63
    Activations Density 0.003%

    No Known Activations