© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169661
    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_56_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
     class
    0.50
     classes
    0.49
    類
    0.45
     so
    0.44
     classe
    0.43
    类
    0.43
    class
    0.42
    Class
    0.40
    類の
    0.38
     kelas
    0.38
    POSITIVE LOGITS
     par
    0.53
    par
    0.44
     हमको
    0.41
    taste
    0.41
     DATA
    0.39
    together
    0.39
    我们会
    0.36
    㚘
    0.35
     together
    0.35
    DATA
    0.35
    Activations Density 0.000%

    No Known Activations