© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17619
    Prev
    Next
    INDEX
    Explanations

    So, For, Ireland, Do, Large

    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
     języ
    0.35
    Monitoring
    0.34
    ある
    0.34
    Cells
    0.34
     sifat
    0.33
     rougeâtres
    0.33
    濂
    0.33
    Changes
    0.31
    Regulations
    0.31
    EC
    0.31
    POSITIVE LOGITS
    ొ
    0.32
    ته
    0.30
     trolley
    0.30
     খুলনা
    0.30
    hement
    0.29
     heinous
    0.29
    rimidine
    0.29
    пусти
    0.28
    ઃ
    0.28
     Ди
    0.28
    Activations Density 0.014%

    No Known Activations