© 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. 170882
    Prev
    Next
    INDEX
    Explanations

    molecule

    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
    Not in Any Lists

    No Comments

    Negative Logits
    分
    0.69
     раз
    0.56
     roz
    0.54
     raz
    0.51
    Roz
    0.49
     Roz
    0.48
    Raz
    0.48
     phân
    0.46
    roz
    0.46
    분
    0.44
    POSITIVE LOGITS
     molecular
    2.78
     Molecular
    2.63
    Molecular
    2.52
    molecular
    2.48
     молеку
    2.44
    分子
    2.25
     mole
    2.23
     Mole
    1.94
     molé
    1.92
    Mole
    1.92
    Activations Density 0.011%

    No Known Activations