© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 102562
    Prev
    Next
    INDEX
    Explanations

    foreign names languages

    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_44_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
    Pablo
    0.41
    Papa
    0.41
    挥
    0.39
    بري
    0.38
    ె
    0.37
     রাজশাহী
    0.37
    κες
    0.37
    菪
    0.37
     разом
    0.37
     уто
    0.36
    POSITIVE LOGITS
    봄
    0.43
     Audi
    0.41
     अंग्रे
    0.39
     Tower
    0.39
     August
    0.39
    gbm
    0.39
     SearchView
    0.39
     англий
    0.39
     AudioClip
    0.39
     อังกฤษ
    0.38
    Activations Density 0.042%

    No Known Activations