© 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. 30920
    Prev
    Next
    INDEX
    Explanations

    palindrome or symmetrical

    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
    콤
    0.42
    晹
    0.37
    欬
    0.37
     পাঠানোর
    0.37
    kol
    0.36
    澀
    0.36
    쓸
    0.36
     nonEmpty
    0.35
    comboBox
    0.35
    闶
    0.35
    POSITIVE LOGITS
     symmetrical
    0.96
     symmetric
    0.86
     Symmetry
    0.81
     symmetry
    0.80
     symmet
    0.77
    对称
    0.77
     symmetrically
    0.76
     asymmetries
    0.75
     Symmetric
    0.70
     asymmetry
    0.69
    Activations Density 0.053%

    No Known Activations