© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14586
    Prev
    Next
    INDEX
    Explanations

    leneck

    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_15_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
    isering
    0.50
    ି
    0.48
     Posters
    0.47
    Of
    0.46
    MQ
    0.44
    𝙏
    0.44
    OF
    0.44
    ሺ
    0.43
    Oil
    0.42
    Với
    0.42
    POSITIVE LOGITS
     wymag
    0.56
     acara
    0.52
     pendapatan
    0.51
     penurunan
    0.51
     vista
    0.50
     menawarkan
    0.50
    ายุ
    0.49
     klien
    0.48
     pierws
    0.48
     sejahtera
    0.48
    Activations Density 0.001%

    No Known Activations