© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32677
    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_31_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
     stronę
    0.40
    Typography
    0.37
    xaml
    0.36
    Kann
    0.36
     للط
    0.36
    辑
    0.36
     formatter
    0.35
    ԁ
    0.35
     adresse
    0.35
    ധിപ
    0.35
    POSITIVE LOGITS
     squaring
    0.40
     eh
    0.39
     MyDB
    0.38
     Dijkstra
    0.38
     olsa
    0.38
    скопа
    0.37
     obstacle
    0.36
    有名な
    0.36
    ابقه
    0.35
     volumes
    0.35
    Activations Density 0.000%

    No Known Activations