© 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. 37574
    Prev
    Next
    INDEX
    Explanations

    contraindicated coverage routinely evidence

    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
     serpentine
    0.64
    representative
    0.57
    undur
    0.57
    ృద్ధి
    0.55
    弇
    0.55
    entlichen
    0.55
    yaml
    0.52
    korn
    0.52
     하여
    0.51
     மிகு
    0.51
    POSITIVE LOGITS
    ز
    0.57
    з
    0.57
    לה
    0.54
     logged
    0.52
    вка
    0.52
    ف
    0.52
     be
    0.50
     quand
    0.50
    fil
    0.50
    esthesia
    0.50
    Activations Density 0.028%

    No Known Activations