© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 66304
    Prev
    Next
    INDEX
    Explanations

    schooling

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    wię
    0.40
     콜
    0.39
    Ud
    0.39
     Rost
    0.38
    డయ
    0.38
    ilov
    0.38
    uZ
    0.38
    콜
    0.38
    दिन
    0.37
     unhappy
    0.37
    POSITIVE LOGITS
     school
    0.96
    school
    0.92
     scuola
    0.78
     स्कूल
    0.77
    School
    0.75
     escuela
    0.75
     шко
    0.71
     স্কুলে
    0.71
     escola
    0.70
     школе
    0.70
    Activations Density 0.001%

    No Known Activations