© 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. 91811
    Prev
    Next
    INDEX
    Explanations

    jet age, jazz age, charter

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ت
    0.75
    ри
    0.69
    ع
    0.67
    ева
    0.65
    т
    0.65
    ون
    0.64
    v
    0.60
    el
    0.59
    ાઇ
    0.59
    ó
    0.59
    POSITIVE LOGITS
     disadvantages
    0.55
     inviting
    0.51
     Jet
    0.51
     thoſe
    0.51
     invites
    0.49
     Comment
    0.48
     Molding
    0.47
    Corre
    0.46
     Specifications
    0.46
     Burst
    0.46
    Activations Density 0.000%

    No Known Activations