© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30106
    Prev
    Next
    INDEX
    Explanations

    deepen understanding

    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_10_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
    ।
    0.83
    ing
    0.82
    at
    0.78
    。
    0.77
     be
    0.77
     reduziert
    0.74
    );
    0.72
    r
    0.70
    <0x80>
    0.70
    0
    0.70
    POSITIVE LOGITS
     Increases
    0.72
    یر
    0.71
    اتی
    0.70
    لی
    0.64
    ड़
    0.63
    𐰚
    0.63
    ابی
    0.63
    زی
    0.59
    دی
    0.59
     adsorption
    0.59
    Activations Density 0.032%

    No Known Activations