© 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. 207573
    Prev
    Next
    INDEX
    Explanations

    sun

    np_max-act-logits · gemini-2.5-flash-lite
    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
     tree
    2.28
    tree
    1.96
     Tree
    1.93
    Tree
    1.80
     TREE
    1.68
    树
    1.61
    TREE
    1.57
    樹
    1.52
     árbol
    1.36
     árvore
    1.23
    POSITIVE LOGITS
    Bened
    0.38
    Dropout
    0.37
    ները
    0.37
     silice
    0.37
    邺
    0.35
     नीला
    0.35
     Lorentz
    0.35
    ويلة
    0.35
    ώρα
    0.34
    стере
    0.34
    Activations Density 0.010%

    No Known Activations