© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198978
    Prev
    Next
    INDEX
    Explanations

    sea

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    Elo
    0.39
    bus
    0.39
    喆
    0.38
    raron
    0.38
     vision
    0.37
     خیر
    0.37
    嘏
    0.37
     Vish
    0.36
    Fran
    0.35
    ద్ద
    0.35
    POSITIVE LOGITS
     sea
    0.79
    Sea
    0.74
     Sea
    0.71
    sea
    0.63
    海
    0.54
     море
    0.52
     hải
    0.52
     seaweed
    0.50
     SEA
    0.49
     கடல்
    0.47
    Activations Density 0.049%

    No Known Activations