© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59543
    Prev
    Next
    INDEX
    Explanations

    shellfish

    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_59_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
     shrimp
    0.79
     lobster
    0.74
     Shrimp
    0.74
    🦞
    0.73
     Seafood
    0.69
     shrimps
    0.69
     crayfish
    0.69
     aquaculture
    0.68
     Lobster
    0.67
     mammalian
    0.66
    POSITIVE LOGITS
     crust
    2.09
     Crust
    1.61
     mar
    0.71
     mol
    0.60
    Mar
    0.50
    mol
    0.50
     Moll
    0.50
     мол
    0.50
     몰
    0.48
     moll
    0.48
    Activations Density 0.031%

    No Known Activations