© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9343
    Prev
    Next
    INDEX
    Explanations

    Hawaii and islands

    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_13_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
    𖥔
    0.49
    दयाल
    0.46
     hosszú
    0.45
     dólares
    0.44
    ༻
    0.42
     funcionários
    0.42
     चाहर
    0.42
     konci
    0.42
     मिलियन
    0.41
     недель
    0.41
    POSITIVE LOGITS
     Hawaii
    0.54
     Hawaiian
    0.50
    Hawaii
    0.49
    ोन
    0.46
     Honolulu
    0.45
     Hawai
    0.43
     Maui
    0.42
     }^{\
    0.42
    抑
    0.41
    عر
    0.41
    Activations Density 0.026%

    No Known Activations