© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6253
    Prev
    Next
    INDEX
    Explanations

    Create new Xcode project iOS App

    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_39_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
    上下文
    0.42
    কুল
    0.38
     sekar
    0.37
     ]);
    0.36
     LANA
    0.36
     गिरफ्तार
    0.35
    banana
    0.35
    彈
    0.35
     урока
    0.35
    )}+\
    0.35
    POSITIVE LOGITS
    соб
    0.46
    缴纳
    0.40
     ताम
    0.37
     crew
    0.37
     ideology
    0.37
    IME
    0.37
    ুমাত্র
    0.37
     demethyl
    0.37
     zert
    0.36
    izhou
    0.36
    Activations Density 0.004%

    No Known Activations