© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45572
    Prev
    Next
    INDEX
    Explanations

    base isolation or network interface types

    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
    ة
    0.76
    ي
    0.69
    an
    0.65
    算是
    0.64
    anis
    0.64
    י
    0.64
    erode
    0.63
    ت
    0.63
    жда
    0.62
    *
    0.62
    POSITIVE LOGITS
     lanjut
    0.61
    ロ
    0.58
    𝐩
    0.58
     conglomer
    0.57
    gulation
    0.57
     scars
    0.54
    ถาน
    0.54
    GLOBALS
    0.54
    वैज्ञानिक
    0.54
    ફ
    0.54
    Activations Density 0.003%

    No Known Activations