© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232429
    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_6_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
    س
    1.12
    á
    1.09
    ف
    1.06
    ling
    1.03
    یک
    1.01
    liners
    0.97
    ó
    0.95
    з
    0.92
     of
    0.92
    ود
    0.90
    POSITIVE LOGITS
    a
    1.15
    他
    0.98
     contenuto
    0.97
    ことなく
    0.93
     લઈને
    0.93
    Durante
    0.91
     deuxième
    0.90
     furiously
    0.88
     culoare
    0.88
     مدير
    0.87
    Activations Density 0.000%

    No Known Activations