© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215234
    Prev
    Next
    INDEX
    Explanations

    city and administrative divisions

    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_31_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
    Lob
    0.38
    饯
    0.38
    bu
    0.37
     débar
    0.37
     fins
    0.35
     bu
    0.34
    HOW
    0.34
    raiz
    0.34
    湘
    0.34
    roots
    0.34
    POSITIVE LOGITS
     Neighborhood
    0.41
    🌆
    0.40
    市内
    0.39
     ಇದ್ದ
    0.39
     ব্যাব
    0.38
     Ongoing
    0.37
     месяца
    0.36
     amiable
    0.36
     কলকাতায়
    0.36
     카드
    0.36
    Activations Density 0.000%

    No Known Activations