© 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. 37968
    Prev
    Next
    INDEX
    Explanations

    earthmoving or mail dataset

    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
     universidad
    0.61
     четы
    0.57
     φ
    0.55
     farmac
    0.54
     aldehyde
    0.54
     동일
    0.54
     constitución
    0.53
    мма
    0.52
     kompos
    0.52
    ਰੇ
    0.52
    POSITIVE LOGITS
    mousedown
    0.57
    cen
    0.54
    껐
    0.53
    pressed
    0.52
    acket
    0.51
    bibitem
    0.50
    lookup
    0.49
    to
    0.48
    keV
    0.48
     Redskins
    0.48
    Activations Density 0.000%

    No Known Activations