© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195415
    Prev
    Next
    INDEX
    Explanations

    US Army and Air Force

    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_27_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
     conveying
    0.42
    सुम
    0.40
     perceiving
    0.40
     delivered
    0.37
     conveyed
    0.36
    휋
    0.36
     delivering
    0.35
     decolor
    0.35
     earthen
    0.35
    ামিটার
    0.35
    POSITIVE LOGITS
    勲
    0.43
     afsl
    0.39
     от
    0.39
     есть
    0.38
     Respiratory
    0.38
    終了
    0.37
     incrível
    0.37
     ફ
    0.36
     විය
    0.36
     från
    0.36
    Activations Density 0.001%

    No Known Activations