© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14155
    Prev
    Next
    INDEX
    Explanations

    aviation and spacecraft components

    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_13_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
    ্রম
    0.50
     varchar
    0.49
     Verdana
    0.46
    %.
    0.45
    را
    0.45
    滦
    0.45
     anxious
    0.45
    %"
    0.44
    \
    0.43
    гом
    0.43
    POSITIVE LOGITS
    боры
    0.50
    planes
    0.49
    flights
    0.48
    飛行
    0.48
     kites
    0.48
    includes
    0.47
    Rocket
    0.47
    getFlight
    0.46
    ppling
    0.46
    अर्स
    0.46
    Activations Density 0.030%

    No Known Activations