© 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. 50463
    Prev
    Next
    INDEX
    Explanations

    three.js libraries

    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
    ূ
    0.37
     Friedman
    0.36
    Exist
    0.35
    regulatory
    0.35
    ర
    0.35
    ******
    0.34
    ács
    0.34
    menin
    0.34
     व्यायाम
    0.34
    }$.
    0.34
    POSITIVE LOGITS
     perfekt
    0.37
     pinched
    0.36
     potrebno
    0.35
     軍
    0.35
    ロード
    0.34
     objek
    0.34
     Dame
    0.34
    സ്‌
    0.34
    ateri
    0.34
     Lap
    0.33
    Activations Density 0.032%

    No Known Activations