© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60272
    Prev
    Next
    INDEX
    Explanations

    lightweight (comparisons or descriptions)

    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
    Processor
    0.60
    не
    0.58
     ஒற்று
    0.58
    Disease
    0.57
    к
    0.57
    нов
    0.57
     అమ్మ
    0.57
    Crop
    0.56
    irmeye
    0.56
    나
    0.56
    POSITIVE LOGITS
    s
    0.73
    </h4>
    0.64
    d
    0.58
     Into
    0.57
    ត្រូវការ
    0.54
     το
    0.53
     locomotives
    0.52
     "
    0.52
    –
    0.51
     généralement
    0.51
    Activations Density 0.002%

    No Known Activations