© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1293
    Prev
    Next
    INDEX
    Explanations

    refugees and migration crises

    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_39_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
     እየሱስ
    0.45
     coconut
    0.42
    coconut
    0.42
    蔚
    0.39
    ciaux
    0.39
    兀
    0.39
    CHES
    0.38
    ൯
    0.38
    復活
    0.37
     ihop
    0.36
    POSITIVE LOGITS
     refugee
    2.13
     refugees
    1.97
     Refugee
    1.88
     Refugees
    1.80
     refugi
    1.67
     শরণার্থী
    1.59
     Flücht
    1.59
     fleeing
    1.48
     refug
    1.39
     refuge
    1.36
    Activations Density 0.071%

    No Known Activations