© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141180
    Prev
    Next
    INDEX
    Explanations

    airport terminology

    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
    st
    0.59
    0.57
    sk
    0.54
    th
    0.52
    s
    0.51
    I
    0.49
    rak
    0.48
    sa
    0.48
    t
    0.48
    sko
    0.46
    POSITIVE LOGITS
     ゲーム
    0.59
    қу
    0.58
     Fisheries
    0.57
     کی
    0.53
     fisheries
    0.53
     gioco
    0.52
     필요한
    0.52
    पिछ
    0.52
     currentGame
    0.51
    கரு
    0.51
    Activations Density 0.000%

    No Known Activations