© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37913
    Prev
    Next
    INDEX
    Explanations

    printers, scanners, paper jams

    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_11_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
    на
    0.57
    ที่
    0.57
     Swedish
    0.56
     will
    0.56
    ми
    0.56
     marble
    0.55
    の
    0.54
    ники
    0.53
    が
    0.53
    կ
    0.52
    POSITIVE LOGITS
    bet
    0.59
    for
    0.58
    printf
    0.55
    kannten
    0.54
    inat
    0.53
     ['(?
    0.51
    JSPA
    0.50
    gadas
    0.50
     προσ
    0.50
    ParallelGroup
    0.50
    Activations Density 0.022%

    No Known Activations