© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35379
    Prev
    Next
    INDEX
    Explanations

    island

    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
     कपिल
    0.40
     ventricle
    0.38
    ❮
    0.38
     internalization
    0.37
     tég
    0.37
    埼玉
    0.37
    ilee
    0.36
    CAPTURE
    0.36
     హిట్
    0.36
    哟
    0.36
    POSITIVE LOGITS
     island
    0.95
    island
    0.88
     Island
    0.80
    Island
    0.79
    岛
    0.75
     pulau
    0.73
     islands
    0.72
     섬
    0.71
     остров
    0.70
     Adası
    0.68
    Activations Density 0.038%

    No Known Activations