© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122363
    Prev
    Next
    INDEX
    Explanations

    embedded systems and code setup

    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_37_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
     code
    0.41
    码
    0.39
     kodu
    0.39
     -=
    0.38
     ki
    0.38
    代码
    0.37
    釀
    0.37
     lif
    0.37
     khiển
    0.37
     lifes
    0.37
    POSITIVE LOGITS
    配置文件
    0.41
    谘
    0.41
     violinist
    0.40
     တယ်
    0.38
    ilitas
    0.36
    roje
    0.36
    outFile
    0.36
    boxylate
    0.36
    OF
    0.35
     fichero
    0.35
    Activations Density 0.004%

    No Known Activations