© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141964
    Prev
    Next
    INDEX
    Explanations

    immigration / asylum / refugees

    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_12_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
     years
    0.61
     مض
    0.49
     YEARS
    0.47
     মন্ত্রিস
    0.47
     godina
    0.47
     anos
    0.46
     چند
    0.46
    懵
    0.46
    igated
    0.45
     yıll
    0.45
    POSITIVE LOGITS
    Bret
    0.56
     froid
    0.54
    Suzanne
    0.52
     Faye
    0.52
     couverture
    0.52
    étr
    0.51
     être
    0.50
     richesse
    0.50
     Suzanne
    0.50
    স্‌
    0.49
    Activations Density 0.000%

    No Known Activations