© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32479
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_7_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
     presentes
    0.54
    们的
    0.54
     les
    0.47
    /
    0.46
    {
    0.46
     componentes
    0.44
    成品
    0.43
    用
    0.43
    趁
    0.41
     votos
    0.41
    POSITIVE LOGITS
    nerv
    0.53
     स्वप्
    0.52
    ahorse
    0.51
    utama
    0.50
     Shanghai
    0.50
    χή
    0.50
    verk
    0.50
     કેટલાક
    0.50
     ವಿರುದ್ಧ
    0.50
     Hanks
    0.50
    Activations Density 0.000%

    No Known Activations