© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10912
    Prev
    Next
    INDEX
    Explanations

    capital of Belgium

    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_40_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
     nowhere
    0.43
     anywhere
    0.41
    謄
    0.41
     Somewhere
    0.40
    ির্ব
    0.39
     serum
    0.39
     tape
    0.37
    替
    0.36
     الآن
    0.36
     understandable
    0.36
    POSITIVE LOGITS
     tiu
    0.45
    HAS
    0.41
     BBS
    0.41
     Ephesus
    0.39
    fungen
    0.39
     Buzz
    0.38
     Reyes
    0.38
    cijas
    0.38
    icz
    0.38
    鈴木
    0.38
    Activations Density 0.013%

    No Known Activations