© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134082
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
     taxis
    0.38
    ಂಪ
    0.38
    niej
    0.35
    cyte
    0.35
    腈
    0.35
    без
    0.35
    ân
    0.34
     לת
    0.34
    dex
    0.34
     Hatt
    0.34
    POSITIVE LOGITS
    Bill
    0.40
     मू
    0.39
     venn
    0.38
    ိုး
    0.37
     Eliot
    0.37
    优
    0.37
     DSG
    0.37
    Lincoln
    0.36
     Lincoln
    0.35
    IamPermissions
    0.35
    Activations Density 0.000%

    No Known Activations