© 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. 206029
    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
    thed
    0.80
    g
    0.66
     jednego
    0.59
    essentially
    0.58
     their
    0.57
    which
    0.55
    l
    0.55
    ergy
    0.55
     entière
    0.54
     preconceived
    0.54
    POSITIVE LOGITS
     to
    0.61
     on
    0.61
    to
    0.60
    >×</
    0.60
    חר
    0.56
    ذلك
    0.54
    زي
    0.54
    كره
    0.54
    بي
    0.54
    ון
    0.54
    Activations Density 0.000%

    No Known Activations