© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32007
    Prev
    Next
    INDEX
    Explanations

    code comments and tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     ಹಾಗ
    0.37
     CCOC
    0.36
     Strugg
    0.36
    ববার
    0.35
    Door
    0.34
    拔
    0.34
    window
    0.34
     EOF
    0.33
    CCOC
    0.33
    ="("
    0.32
    POSITIVE LOGITS
     রাইফ
    0.42
    FlatStyle
    0.39
    ॉज
    0.39
     stools
    0.38
    MenuStyle
    0.38
    يكل
    0.37
     Recipes
    0.37
    মোট
    0.36
    Recipes
    0.36
     clone
    0.36
    Activations Density 0.000%

    No Known Activations