© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165474
    Prev
    Next
    INDEX
    Explanations

    population density and distribution

    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
    ida
    0.54
     "]
    0.46
     quei
    0.45
    rides
    0.45
    uos
    0.45
     iniziale
    0.45
     pelig
    0.44
    enda
    0.43
    TEA
    0.43
     probable
    0.43
    POSITIVE LOGITS
     actionBar
    0.57
     Ereign
    0.52
     Ви
    0.51
     Игра
    0.51
    נ
    0.51
    ვ
    0.50
    ﺮ
    0.50
    ви
    0.50
     Ernährung
    0.50
     छठ
    0.50
    Activations Density 0.001%

    No Known Activations