© 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. 92774
    Prev
    Next
    INDEX
    Explanations

    covered / contains information

    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
    kach
    0.65
    ку
    0.63
    只有
    0.61
     hanya
    0.59
    ͒
    0.59
    وینت
    0.59
     jedynie
    0.55
    চরা
    0.55
     apenas
    0.54
    களில்
    0.54
    POSITIVE LOGITS
     (
    0.60
    ene
    0.58
    ile
    0.57
    ulare
    0.57
    est
    0.55
    et
    0.53
    ové
    0.53
     (‘
    0.52
     సమ
    0.52
     المؤلف
    0.50
    Activations Density 0.004%

    No Known Activations