© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24531
    Prev
    Next
    INDEX
    Explanations

    vectors

    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_56_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
     مقام
    0.41
    SARS
    0.40
     Pepe
    0.39
     Hepatitis
    0.39
    covid
    0.39
    韆
    0.39
    umes
    0.38
    防疫
    0.38
    เท่านั้น
    0.37
    祉
    0.37
    POSITIVE LOGITS
     vector
    2.03
     Vector
    1.93
    Vector
    1.90
    vector
    1.84
     vectors
    1.66
     vektor
    1.61
     벡터
    1.56
     VECTOR
    1.55
     Vectors
    1.54
     вектор
    1.52
    Activations Density 0.028%

    No Known Activations