© 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. 166887
    Prev
    Next
    INDEX
    Explanations

    javascript code blocks

    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
     Erie
    0.39
     anisotropic
    0.38
     Guelph
    0.38
     eff
    0.37
    웅
    0.36
    궜
    0.36
     frust
    0.36
     setting
    0.36
     regarding
    0.36
     anhydrous
    0.36
    POSITIVE LOGITS
    (__
    0.38
    Analysts
    0.38
     Exports
    0.36
    iega
    0.36
    زى
    0.36
    ಾಗಲೇ
    0.35
    embangunan
    0.35
     निवास
    0.35
    distan
    0.34
    忘记
    0.34
    Activations Density 0.000%

    No Known Activations