© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197622
    Prev
    Next
    INDEX
    Explanations

    most well-known

    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_4_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
    in
    0.86
    п
    0.86
    е
    0.80
    𝘪
    0.75
    ра
    0.72
    ጇ
    0.72
     quản
    0.71
    你
    0.71
    on
    0.70
    {
    0.70
    POSITIVE LOGITS
    dengan
    0.86
    ne
    0.82
    nombre
    0.77
     artefacts
    0.73
     द्वारा
    0.72
     reconciling
    0.69
     eliminado
    0.69
     duplicating
    0.69
     modifié
    0.68
    🏻
    0.68
    Activations Density 0.001%

    No Known Activations