© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 241895
    Prev
    Next
    INDEX
    Explanations

    loop termination constructs

    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_40_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
    急
    0.38
    Illinois
    0.38
    終了
    0.38
    结束
    0.37
    Constants
    0.37
    apiRequest
    0.37
    static
    0.37
    end
    0.36
    IList
    0.36
     endTime
    0.36
    POSITIVE LOGITS
     kontroll
    0.45
     contained
    0.40
     shaved
    0.38
     Ox
    0.38
     lunchtime
    0.38
     ★★
    0.38
     perteneciente
    0.38
     controlado
    0.38
    "),],
    0.37
     oxyd
    0.37
    Activations Density 0.004%

    No Known Activations