© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216892
    Prev
    Next
    INDEX
    Explanations

    silk

    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_50_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
    Jessica
    0.53
     Jessica
    0.48
     Dal
    0.45
    Dal
    0.41
     Dalton
    0.41
    💒
    0.40
     PAUL
    0.39
     Paul
    0.38
    Paul
    0.37
    Jess
    0.37
    POSITIVE LOGITS
    絲
    0.41
     tils
    0.39
     silk
    0.39
     silks
    0.39
    खर
    0.38
     tand
    0.38
     Gé
    0.38
    Silk
    0.37
     Byers
    0.37
     Francis
    0.37
    Activations Density 0.030%

    No Known Activations