© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199063
    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_27_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
     Vishal
    0.38
     опубли
    0.38
     shar
    0.38
     давайте
    0.37
    ")}}
    0.36
     发布
    0.36
     Newsletter
    0.36
     Video
    0.36
     publicó
    0.36
     ПК
    0.36
    POSITIVE LOGITS
     exercitation
    0.38
     PHYSICS
    0.37
     traitements
    0.35
     ድ
    0.35
    ্যন্ত
    0.33
     rameaux
    0.33
     ਗ
    0.33
    وڑ
    0.33
    ريبات
    0.33
     BATH
    0.33
    Activations Density 0.000%

    No Known Activations