© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9062
    Prev
    Next
    INDEX
    Explanations

    junior, lead, support roles

    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_40_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
    ORGE
    0.45
    Fullscreen
    0.39
    كنولوجيا
    0.38
    政府采购
    0.37
    ራዊ
    0.37
    FloatField
    0.36
     ലാ
    0.36
    阵
    0.35
     гара
    0.35
     pronouns
    0.35
    POSITIVE LOGITS
     Support
    0.62
     support
    0.62
    Support
    0.59
    support
    0.54
     सपोर्ट
    0.54
     SUPPORT
    0.50
     Supports
    0.46
    支持
    0.45
     dukungan
    0.45
     समर्थन
    0.44
    Activations Density 0.081%

    No Known Activations