© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139117
    Prev
    Next
    INDEX
    Explanations

    Hong Kong districts and services

    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_12_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
    rend
    0.51
    REIB
    0.49
    爀
    0.49
    RIS
    0.46
    vVertex
    0.46
    niji
    0.46
    lichkeiten
    0.45
    reth
    0.44
    arendon
    0.44
    CHN
    0.44
    POSITIVE LOGITS
     Nawab
    0.56
     $@
    0.45
     ราย
    0.44
     Mughal
    0.43
    ována
    0.43
     ba
    0.43
     yar
    0.43
     Gal
    0.42
    ocaine
    0.42
    ॅन
    0.42
    Activations Density 0.002%

    No Known Activations