© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40645
    Prev
    Next
    INDEX
    Explanations

    weekly reports, warranties, sunny daytime, personal life

    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_3_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
     K
    0.98
    L
    0.90
    B
    0.90
    F
    0.90
    H
    0.86
    Client
    0.84
     D
    0.83
    ↵
    0.82
     M
    0.82
     H
    0.81
    POSITIVE LOGITS
    QAry
    0.82
    ی
    0.80
    می
    0.78
     وی
    0.74
    роз
    0.73
     он
    0.73
     она
    0.73
    ルの
    0.73
    やかな
    0.71
    ності
    0.71
    Activations Density 0.040%

    No Known Activations