© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199583
    Prev
    Next
    INDEX
    Explanations

    square root simplification

    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
    វា
    0.41
     wody
    0.40
    ដូច
    0.39
    ሣ
    0.39
     Misalnya
    0.37
     ruler
    0.37
     cushions
    0.37
     dibagi
    0.37
     пределах
    0.36
    ധാ
    0.36
    POSITIVE LOGITS
    長期
    0.39
    優秀
    0.38
    Nov
    0.37
    newTask
    0.37
    novation
    0.37
    illiant
    0.37
    情
    0.36
     quiero
    0.36
    vist
    0.36
    採用
    0.36
    Activations Density 0.001%

    No Known Activations