© 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. 121033
    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
    
    0.40
    貨
    0.39
     zve
    0.38
    Ặ
    0.38
    pperware
    0.38
     NAMES
    0.37
    শন
    0.37
    ertools
    0.36
    Programme
    0.36
    끊
    0.36
    POSITIVE LOGITS
     acknowledged
    0.41
     encased
    0.39
     დიდი
    0.38
     recognized
    0.38
     dangerously
    0.38
    ິ່ງ
    0.36
    क्सीडेंट
    0.36
     included
    0.36
     redes
    0.36
     acknowledge
    0.36
    Activations Density 0.000%

    No Known Activations