© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85686
    Prev
    Next
    INDEX
    Explanations

    non-

    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_3_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
    ہ
    0.77
    ছিলেন
    0.73
    ส
    0.70
    し
    0.68
    </strong>
    0.68
     दरबार
    0.67
    </h2>
    0.66
    </code>
    0.65
    ş
    0.65
    >
    0.64
    POSITIVE LOGITS
    at
    0.75
     poč
    0.65
    ou
    0.58
    was
    0.57
     informs
    0.57
     BufferedImage
    0.57
    AC
    0.56
     brevity
    0.56
    ιου
    0.55
     tradu
    0.55
    Activations Density 0.008%

    No Known Activations