© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11968
    Prev
    Next
    INDEX
    Explanations

    place names and addresses

    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
     qubits
    0.18
     δύο
    0.18
     três
    0.18
    ИН
    0.17
     erhöhen
    0.17
    ERRY
    0.17
    𝒐
    0.17
    Анд
    0.17
     three
    0.17
     আয়নগুলি
    0.17
    POSITIVE LOGITS
     படைய
    0.14
    kis
    0.14
    wick
    0.14
    Tela
    0.13
     pedig
    0.13
    weisung
    0.13
     شعب
    0.13
    \%.
    0.13
    Vere
    0.13
    ワゴン
    0.13
    Activations Density 0.031%

    No Known Activations