© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 88574
    Prev
    Next
    INDEX
    Explanations

    saliva production or collection

    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_18_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
     वर्णन
    0.46
    mmm
    0.46
     નક્
    0.45
    兹
    0.44
     swoop
    0.43
    胄
    0.43
    均匀
    0.42
    arounds
    0.42
     fascinated
    0.42
    ियमित
    0.42
    POSITIVE LOGITS
     anno
    0.46
    ס
    0.45
    เพ
    0.44
    olines
    0.44
    س
    0.43
    Family
    0.43
    ässer
    0.43
    Bigg
    0.42
     इ
    0.42
    انو
    0.42
    Activations Density 0.000%

    No Known Activations