© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 27-GEMMASCOPE-2-TRANSCODER-262K
    4. 118383
    Prev
    Next
    INDEX
    Explanations

    is_active or boolean flags

    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
    ंशी
    0.46
     conflicto
    0.45
     bahas
    0.42
    .[/
    0.41
    щё
    0.40
    .-\
    0.40
    йно
    0.40
    струк
    0.39
     institución
    0.39
    、​
    0.39
    POSITIVE LOGITS
     Memorial
    0.47
     ঈশ্বরের
    0.42
     Senior
    0.41
     Observatory
    0.41
     Circle
    0.39
     Sample
    0.39
     abandoned
    0.39
     Theorem
    0.39
     തി
    0.38
     River
    0.37
    Activations Density 0.000%

    No Known Activations