© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77555
    Prev
    Next
    INDEX
    Explanations

    existing plurals and verb endings

    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_31_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
    死亡
    0.77
    death
    0.74
     ölüm
    0.73
     kematian
    0.72
     death
    0.71
     śmierci
    0.70
     muerte
    0.70
    灭
    0.68
     মৃত্যুর
    0.68
    termination
    0.67
    POSITIVE LOGITS
     revisit
    0.35
     좌표
    0.35
    क्तिक
    0.34
     tackles
    0.33
     বালক
    0.33
     তাক
    0.33
     wavefront
    0.33
     ஈர
    0.33
    ற்ச
    0.32
     Bunda
    0.32
    Activations Density 0.034%

    No Known Activations