© 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. 126153
    Prev
    Next
    INDEX
    Explanations

    world's most

    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
     ஒப்ப
    0.67
    Ǘ
    0.65
     millennia
    0.64
    an
    0.63
     world
    0.63
    gunakan
    0.62
     quatern
    0.59
     جهانی
    0.59
     MET
    0.59
     קי
    0.58
    POSITIVE LOGITS
    س
    0.86
    с
    0.83
    ർ
    0.81
    ية
    0.74
    ：
    0.73
    2
    0.72
    ون
    0.72
    د
    0.71
    ര്‍
    0.71
    á
    0.70
    Activations Density 0.001%

    No Known Activations