© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 196858
    Prev
    Next
    INDEX
    Explanations

    diverse languages

    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_50_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
    เติม
    0.66
    Ag
    0.46
     trưởng
    0.44
    fill
    0.43
    장은
    0.42
    ोत्
    0.40
    ُونَ
    0.40
    苌
    0.40
    ເຕ
    0.39
    填
    0.39
    POSITIVE LOGITS
     സൂര്യ
    0.41
     Rai
    0.39
     sœurs
    0.38
    üsü
    0.38
     ruffle
    0.38
    razia
    0.38
     vol
    0.37
     Knob
    0.37
    кан
    0.37
     ধর্ষণের
    0.37
    Activations Density 0.000%

    No Known Activations