© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14127
    Prev
    Next
    INDEX
    Explanations

    caused by, made up, driven by

    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_15_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
     \{
    0.43
     خو
    0.43
    ifying
    0.39
     छोर
    0.39
    adır
    0.38
     }-\
    0.37
    Delegate
    0.37
    rijk
    0.36
    asına
    0.36
    ারন
    0.36
    POSITIVE LOGITS
    м
    0.45
    九
    0.40
    es
    0.40
    ین
    0.39
    тов
    0.39
    로
    0.39
    ت
    0.38
    cc
    0.38
    م
    0.37
    模型
    0.37
    Activations Density 0.076%

    No Known Activations