© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 183104
    Prev
    Next
    INDEX
    Explanations

    equal to

    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_29_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
     lost
    0.42
     missed
    0.37
     VAT
    0.36
    符合
    0.34
     obvi
    0.34
    pto
    0.34
    混
    0.34
    VAT
    0.34
     அமைந்துள்ளது
    0.33
    MEs
    0.33
    POSITIVE LOGITS
    setBadgeText
    0.37
    Без
    0.37
    рсә
    0.36
    არი
    0.35
    ;(
    0.35
    ArchiveAction
    0.34
     صفحۀ
    0.33
     transaksi
    0.33
    Выберите
    0.33
    驩
    0.33
    Activations Density 0.003%

    No Known Activations