© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117271
    Prev
    Next
    INDEX
    Explanations

    USA addresses

    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_27_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
     Fj
    0.34
    onego
    0.33
     rf
    0.33
    ラーメン
    0.33
     کنه
    0.32
    ሖ
    0.32
     संतान
    0.32
     जोग
    0.32
     جائے۔
    0.31
     Joomla
    0.31
    POSITIVE LOGITS
    笺
    0.36
    PQ
    0.34
    סק
    0.33
    SerialNumber
    0.33
     பாதுகா
    0.32
     mediocr
    0.32
    SearchResults
    0.32
     coastal
    0.32
    डॉ
    0.32
    單位
    0.31
    Activations Density 0.006%

    No Known Activations