© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64740
    Prev
    Next
    INDEX
    Explanations

    Honda, Civic, Accord, Acura

    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_41_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
    жим
    0.46
    ()==
    0.41
    ==-
    0.41
     Gustavo
    0.40
     זי
    0.40
    Gust
    0.39
    avro
    0.39
     ইউনি
    0.39
    )==
    0.38
    ფ
    0.38
    POSITIVE LOGITS
     Honda
    0.99
     Hond
    0.98
    Honda
    0.89
     hond
    0.89
     Civic
    0.85
     honda
    0.85
     civic
    0.66
     Accord
    0.66
     accord
    0.63
     Acura
    0.63
    Activations Density 0.001%

    No Known Activations