© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34350
    Prev
    Next
    INDEX
    Explanations

    Wyoming and Montenegro

    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_31_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
     හේ
    0.40
     हीट
    0.39
     गर्भावस्था
    0.39
    abort
    0.38
    🤰
    0.38
    관리
    0.38
     관리
    0.37
     nace
    0.37
    ແບບ
    0.37
    寢
    0.37
    POSITIVE LOGITS
     Wyoming
    0.46
     Montenegro
    0.44
    Montana
    0.42
     Montana
    0.42
     मिलकर
    0.41
     Albanian
    0.41
     Mason
    0.40
     Yellowstone
    0.40
     Yugoslav
    0.38
    Mason
    0.37
    Activations Density 0.019%

    No Known Activations