© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101211
    Prev
    Next
    INDEX
    Explanations

    sql string concatenation

    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_14_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
    ﾝ
    0.61
    for
    0.59
    לב
    0.58
     optimizing
    0.56
    러스
    0.55
     どう
    0.55
    न्दर
    0.54
    тке
    0.54
    퉁
    0.53
    otherArchive
    0.52
    POSITIVE LOGITS
    Name
    0.74
     is
    0.71
    Lo
    0.68
    Background
    0.64
    Is
    0.63
    Id
    0.62
    ă
    0.60
    She
    0.59
    Val
    0.59
    Date
    0.59
    Activations Density 0.005%

    No Known Activations