© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4569
    Prev
    Next
    INDEX
    Explanations

    URLs with digits and letters

    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_39_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
    ्यूस
    0.49
     ஊராட்சி
    0.39
    NumberOperation
    0.35
    ccionar
    0.35
    rophiles
    0.35
    œ
    0.34
    UIManager
    0.34
    missive
    0.34
     Kurs
    0.34
    چے
    0.34
    POSITIVE LOGITS
     AC
    0.42
     Quattro
    0.39
    Spending
    0.37
    MULT
    0.37
    AC
    0.36
    Att
    0.36
    น่า
    0.35
    ምን
    0.35
    ပြီး
    0.35
    圃
    0.35
    Activations Density 0.010%

    No Known Activations