© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217266
    Prev
    Next
    INDEX
    Explanations

    skill and knowledge expression

    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
     ማን
    0.42
     असिस्टेंट
    0.38
     Sticks
    0.37
    惊
    0.37
     অপ
    0.36
    DbType
    0.36
    lew
    0.36
     ఎవ
    0.35
    angular
    0.35
    ரை
    0.35
    POSITIVE LOGITS
    Clone
    0.38
     requested
    0.36
     datar
    0.36
     কমিশন
    0.36
    >)</
    0.35
     legitim
    0.35
     ზე
    0.34
     alue
    0.34
     esetben
    0.34
    AreaData
    0.34
    Activations Density 0.002%

    No Known Activations