© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45058
    Prev
    Next
    INDEX
    Explanations

    Aetherium, ite, Passive

    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
     matériel
    0.77
     chargé
    0.72
     spectre
    0.66
     conserver
    0.64
     underrated
    0.62
    ジネス
    0.61
    م
    0.61
    㷫
    0.60
     projet
    0.59
     certainement
    0.59
    POSITIVE LOGITS
    ll
    0.86
    る
    0.75
    selecting
    0.69
    ↵↵
    0.68
    li
    0.68
    x
    0.68
    text
    0.67
     a
    0.64
    phosphate
    0.64
    reactions
    0.64
    Activations Density 0.013%

    No Known Activations