© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35472
    Prev
    Next
    INDEX
    Explanations

    Six Sigma

    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_11_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
     อังกฤษ
    0.62
     अनुशासन
    0.57
    糇
    0.56
     服务
    0.55
     因為
    0.55
     వ్యవస్థ
    0.55
     ámbitos
    0.54
     श्रृंखला
    0.53
     Porque
    0.53
     більш
    0.53
    POSITIVE LOGITS
    al
    0.59
     wallet
    0.58
    ↵↵
    0.53
    ле
    0.51
    0.48
    <eos>
    0.48
    다
    0.47
    /
    0.47
    ith
    0.46
    та
    0.46
    Activations Density 0.006%

    No Known Activations