© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12905
    Prev
    Next
    INDEX
    Explanations

    code diffs and patch files

    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_13_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
     служба
    0.61
     ,
    0.57
     ก่อน
    0.57
     संख्या
    0.55
     prieš
    0.54
     férias
    0.53
     преди
    0.52
     before
    0.52
    价格
    0.51
     దేశ
    0.51
    POSITIVE LOGITS
    -)
    0.55
    etch
    0.52
    佩
    0.50
    さり
    0.50
    ?)
    0.50
    Inactive
    0.49
    ffiti
    0.49
     quilting
    0.49
     அற்புத
    0.49
    develop
    0.48
    Activations Density 0.000%

    No Known Activations