© 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. 37391
    Prev
    Next
    INDEX
    Explanations

    model of

    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
    ш
    0.77
    bserv
    0.67
     व्यक्ति
    0.64
    र्डिनेट
    0.61
    patial
    0.61
    ton
    0.60
    şan
    0.60
    ں
    0.59
    षित
    0.58
    shoring
    0.58
    POSITIVE LOGITS
    ي
    0.93
    i
    0.85
    י
    0.75
    ి
    0.66
     ouvrir
    0.66
     établ
    0.65
     œufs
    0.65
    ان
    0.64
     auront
    0.64
     cla
    0.63
    Activations Density 0.003%

    No Known Activations