© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 201490
    Prev
    Next
    INDEX
    Explanations

    mobile applications and smartphones

    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_12_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
    ");
    0.65
    lcd
    0.62
    DEST
    0.59
    CITY
    0.59
    lardan
    0.58
    t
    0.58
    lara
    0.57
     enterr
    0.57
    N
    0.57
     wildlife
    0.57
    POSITIVE LOGITS
    ించాడు
    0.46
    endenza
    0.46
     реги
    0.46
     ವಿವಿಧ
    0.45
    ៈ
    0.44
     했던
    0.44
     автомобилей
    0.44
    三十
    0.44
    我們可以
    0.44
    én
    0.43
    Activations Density 0.000%

    No Known Activations