© 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. 91017
    Prev
    Next
    INDEX
    Explanations

    e

    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
    >
    0.61
    public
    0.59
    **
    0.57
    '
    0.55
     v
    0.55
    安
    0.54
    /
    0.52
    cal
    0.52
    ’
    0.51
    {
    0.50
    POSITIVE LOGITS
     testaceis
    0.61
     legado
    0.57
     ಇದೆ
    0.55
     continuamos
    0.55
    স্পতি
    0.55
     आम्हाला
    0.55
    🏬
    0.55
     эту
    0.54
     obat
    0.54
     décadas
    0.54
    Activations Density 0.002%

    No Known Activations