© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51436
    Prev
    Next
    INDEX
    Explanations

    POS- followed by a capitalized word

    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
    ιά
    0.28
     casting
    0.25
    ifié
    0.25
    кова
    0.24
    +="
    0.24
     plus
    0.23
     плюс
    0.23
     الدراسي
    0.23
     твор
    0.23
     insisting
    0.23
    POSITIVE LOGITS
     GOT
    0.27
    ழந்த
    0.25
     cei
    0.24
     HMAC
    0.24
     QTreeWidgetItem
    0.23
     proceeding
    0.23
     świat
    0.23
     nowe
    0.22
    畞
    0.22
     PCs
    0.22
    Activations Density 0.000%

    No Known Activations