© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 508
    Prev
    Next
    INDEX
    Explanations

    javascript module system

    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_38_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
    াঁর
    0.43
    浐
    0.39
    াবাদের
    0.38
    柑
    0.37
    傆
    0.37
    жные
    0.37
    sourceEncoding
    0.36
     situaciones
    0.36
    ీల
    0.36
    ifInterface
    0.36
    POSITIVE LOGITS
     require
    0.57
    require
    0.55
     Require
    0.45
    /******/
    0.42
    Google
    0.40
    </u>
    0.40
     Google
    0.39
     Fresnel
    0.39
    IO
    0.38
     Teles
    0.38
    Activations Density 0.001%

    No Known Activations