© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123411
    Prev
    Next
    INDEX
    Explanations

    memoization

    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
    م
    0.88
    ك
    0.86
    ம்
    0.81
    ्स
    0.81
    á
    0.79
    א
    0.77
    سن
    0.75
    ک
    0.72
    ز
    0.72
    าย
    0.71
    POSITIVE LOGITS
    ol
    0.76
     of
    0.75
     Validación
    0.74
     membrane
    0.71
    ри
    0.70
     and
    0.69
     portée
    0.68
    ossed
    0.68
     Membrane
    0.68
    ),
    0.67
    Activations Density 0.001%

    No Known Activations