© 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. 60456
    Prev
    Next
    INDEX
    Explanations

    se ren, se lever, se reproduire

    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
     to
    0.70
     on
    0.66
     系列
    0.64
    单
    0.64
    Ре
    0.63
    از
    0.61
    Ру
    0.61
    他们
    0.60
    Usuarios
    0.60
    來
    0.59
    POSITIVE LOGITS
     DuPont
    0.56
     året
    0.55
    elbe
    0.55
     kWh
    0.55
    flashdata
    0.54
    жды
    0.54
    IN
    0.53
     vå
    0.53
    ду
    0.52
     noastră
    0.52
    Activations Density 0.000%

    No Known Activations