© 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. 34102
    Prev
    Next
    INDEX
    Explanations

    thermal imaging cameras

    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
    0
    0.74
    дцать
    0.62
    ंद
    0.61
    вает
    0.61
    ీ
    0.58
     базы
    0.57
     are
    0.57
    ೀ
    0.57
    ir
    0.56
    ح
    0.55
    POSITIVE LOGITS
    p
    0.73
    l
    0.70
    或许
    0.64
     ও
    0.62
    NSW
    0.62
    INGS
    0.61
    ほか
    0.61
    m
    0.60
    ৯০
    0.59
    b
    0.59
    Activations Density 0.005%

    No Known Activations