© 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
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91761
    Prev
    Next
    INDEX
    Explanations

    static and dynamic statements

    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_11_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
    getline
    0.45
     वापर
    0.45
     itinéraires
    0.44
    碛
    0.44
     തുറ
    0.43
    :";
    0.43
    ultipl
    0.42
    ሳሪያ
    0.42
    linien
    0.42
    utiliser
    0.41
    POSITIVE LOGITS
     political
    0.57
    یر
    0.47
     precession
    0.45
    ק
    0.45
     político
    0.44
     sociedad
    0.43
     hereditary
    0.43
     treason
    0.43
     vacancy
    0.43
     defeat
    0.43
    Activations Density 0.034%

    No Known Activations