© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126036
    Prev
    Next
    INDEX
    Explanations

    人际关系

    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
    و
    0.66
    K
    0.64
    зге
    0.62
    W
    0.60
    ،
    0.60
    em
    0.57
     suppuration
    0.57
    emiz
    0.56
    th
    0.55
    phus
    0.55
    POSITIVE LOGITS
    യുടെ
    0.71
     financiera
    0.70
    </strong>
    0.70
    чите
    0.69
     effettuare
    0.67
     educativas
    0.66
    et
    0.65
    اي
    0.65
     constantes
    0.65
    т
    0.65
    Activations Density 0.001%

    No Known Activations