© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 171269
    Prev
    Next
    INDEX
    Explanations

    bodies of water

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     lak
    2.00
     Lak
    1.76
    Lak
    1.76
     lac
    1.70
     Lac
    1.66
    Lac
    1.62
    湖
    1.60
    lak
    1.58
     lakeside
    1.56
     Lake
    1.52
    POSITIVE LOGITS
    Rivers
    0.47
     Rivers
    0.44
     rivers
    0.43
    河流
    0.39
    ｬ
    0.39
     Mez
    0.37
    liance
    0.37
    rivers
    0.36
    হাত
    0.36
    柏
    0.35
    Activations Density 0.002%

    No Known Activations