© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234064
    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_32_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
     otvor
    0.40
    সুন্দর
    0.38
    允
    0.38
     cał
    0.38
     aft
    0.37
    ﴿
    0.37
     arch
    0.37
    ympt
    0.37
    <unused78>
    0.36
     सुधा
    0.36
    POSITIVE LOGITS
    Node
    0.43
    Npm
    0.39
    Nodes
    0.38
    Condensed
    0.38
     nodes
    0.37
    шко
    0.37
    Material
    0.37
     Node
    0.36
    ъл
    0.36
     digesting
    0.36
    Activations Density 0.000%

    No Known Activations