© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52580
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    好吧
    0.42
    പ്പെടെ
    0.41
    жливо
    0.40
    ឬ
    0.40
    滖
    0.39
    lemagne
    0.39
     secteurs
    0.38
    CHEMICAL
    0.38
     மாதிர
    0.38
     хоро
    0.37
    POSITIVE LOGITS
     crafted
    0.38
    uyên
    0.36
    キス
    0.36
    Tri
    0.35
    "]/
    0.35
    mless
    0.35
     напомина
    0.34
     धरा
    0.34
    Pairs
    0.33
     கற்ற
    0.33
    Activations Density 0.000%

    No Known Activations