© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23501
    Prev
    Next
    INDEX
    Explanations

    quantities

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    秒
    0.53
    年
    0.48
    年的
    0.43
    posterous
    0.41
    行
    0.41
     个
    0.39
    ú
    0.38
    icorn
    0.37
    년
    0.37
     segundos
    0.36
    POSITIVE LOGITS
    礼
    1.42
    禮
    1.38
     lễ
    1.37
    禮
    0.98
    례
    0.78
     ceremony
    0.77
    月
    0.69
     Ceremony
    0.63
     цере
    0.57
     ceremonia
    0.57
    Activations Density 0.003%

    No Known Activations