© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46471
    Prev
    Next
    INDEX
    Explanations

    place names and people's names

    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_3_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
    。
    0.79
    ש
    0.75
    다
    0.70
    什么
    0.69
    ча
    0.64
     Consultado
    0.63
    0.63
     #{
    0.61
     Dostupné
    0.61
    စဉ်
    0.61
    POSITIVE LOGITS
    it
    1.02
    he
    0.77
    é
    0.77
    í
    0.72
    ach
    0.71
    ów
    0.70
    s
    0.68
    ä
    0.68
    ie
    0.66
    ub
    0.66
    Activations Density 0.000%

    No Known Activations