© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167849
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis or quote

    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_31_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
    ὡ
    0.43
    vang
    0.42
    ቹ
    0.40
     apont
    0.40
    read
    0.39
    ടൊപ്പം
    0.39
     Gemeinde
    0.39
    వరకు
    0.38
     पंचायतों
    0.38
     पंचायत
    0.38
    POSITIVE LOGITS
    issance
    0.39
    濆
    0.39
     encountering
    0.37
     toss
    0.37
    ణు
    0.36
     tossing
    0.36
     encounter
    0.36
     reprint
    0.36
    леку
    0.35
     indexRouter
    0.35
    Activations Density 0.005%

    No Known Activations