© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195467
    Prev
    Next
    INDEX
    Explanations

    "please note:"

    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_15_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
    /
    0.56
     térmica
    0.54
     over
    0.53
    ล็อต
    0.50
     more
    0.48
    दे
    0.48
     imagine
    0.48
    더
    0.48
     which
    0.48
     RAX
    0.48
    POSITIVE LOGITS
    ون
    0.54
     दोन
    0.53
    HTMLElement
    0.51
    ниш
    0.51
    ни
    0.49
    achio
    0.49
    atelier
    0.49
     ثلاثة
    0.48
     četiri
    0.48
    OFFSET
    0.48
    Activations Density 0.002%

    No Known Activations