© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8860
    Prev
    Next
    INDEX
    Explanations

    writing systems, alphabets, and spelling

    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_13_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
    solvent
    0.44
    homogeneous
    0.43
    冰
    0.42
    ench
    0.42
    Ice
    0.41
     solvation
    0.39
    arom
    0.39
    comparing
    0.39
    itect
    0.39
    enche
    0.39
    POSITIVE LOGITS
     Closing
    0.47
     Memorial
    0.46
     Literacy
    0.46
     EC
    0.45
     name
    0.44
     W
    0.43
     имена
    0.43
     nama
    0.42
     UAV
    0.42
     Citizenship
    0.42
    Activations Density 0.064%

    No Known Activations