© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36741
    Prev
    Next
    INDEX
    Explanations

    nearly followed by choking or time

    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
    p
    0.61
     artery
    0.57
    y
    0.56
    其他
    0.55
     quanta
    0.54
     assort
    0.53
     ingen
    0.52
     art
    0.52
     men
    0.52
     caric
    0.52
    POSITIVE LOGITS
    کرات
    0.68
    против
    0.67
    RxDocument
    0.66
    </h3>
    0.64
     BASIS
    0.63
     পুনরায়
    0.63
     ČR
    0.63
     മൂല
    0.61
    мето
    0.61
    pero
    0.60
    Activations Density 0.001%

    No Known Activations