© 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. 4724
    Prev
    Next
    INDEX
    Explanations

    currency names and local currency

    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
    Dou
    0.40
    Sage
    0.38
    fic
    0.38
    FieldSet
    0.38
     sg
    0.38
     пребы
    0.38
    焘
    0.37
     doubly
    0.37
    蛮
    0.37
    jz
    0.36
    POSITIVE LOGITS
     local
    0.69
     мест
    0.63
    Local
    0.62
    LOCAL
    0.62
     Local
    0.61
     местные
    0.61
    local
    0.61
     LOCAL
    0.58
     স্থানীয়
    0.58
     местных
    0.58
    Activations Density 0.057%

    No Known Activations