© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38263
    Prev
    Next
    INDEX
    Explanations

    Korean daily phrases

    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_57_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
     awak
    0.45
    []}
    0.44
    SAL
    0.43
     يو
    0.42
    PARA
    0.40
    Locked
    0.38
    Separate
    0.38
    요
    0.38
     wakes
    0.37
    vening
    0.36
    POSITIVE LOGITS
     넘
    0.43
    enuh
    0.41
    cenie
    0.37
    넘
    0.37
     челове
    0.36
    িত্ব
    0.36
    صرية
    0.36
    ہا
    0.36
     setter
    0.36
     Thames
    0.36
    Activations Density 0.001%

    No Known Activations