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

    Neuronpedia

    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. 51703
    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
    ificado
    0.39
     scrapes
    0.37
    ificar
    0.36
     risulta
    0.36
     scrubs
    0.36
    ੁੱ
    0.35
    សម្រ
    0.35
    ૢ
    0.34
     reservas
    0.34
     keepers
    0.34
    POSITIVE LOGITS
    TRACE
    0.39
     ممن
    0.37
    Trace
    0.37
     निकायों
    0.36
    trimmed
    0.35
    drawing
    0.35
    লিখ
    0.35
    ехали
    0.35
    targeting
    0.34
     방법을
    0.34
    Activations Density 0.000%

    No Known Activations