© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166201
    Prev
    Next
    INDEX
    Explanations

    exponents and mathematical operations

    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_31_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
    [-
    0.40
     means
    0.38
    means
    0.38
     значит
    0.37
     occurs
    0.36
    uega
    0.36
     বৃহৎ
    0.36
     ιδ
    0.34
     Means
    0.34
    >*</
    0.34
    POSITIVE LOGITS
     empl
    0.40
    儂
    0.38
    Astronom
    0.37
     vaik
    0.36
     مؤ
    0.35
    ওল
    0.34
     dek
    0.34
    TOOLS
    0.34
     adolescentes
    0.33
    According
    0.33
    Activations Density 0.001%

    No Known Activations