© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156792
    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_2_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
    4
    1.03
     заповед
    0.98
     sexuales
    0.97
     destacados
    0.94
    ۴
    0.93
    ని
    0.92
    .
    0.92
     europeos
    0.91
    ას
    0.89
     звез
    0.89
    POSITIVE LOGITS
    지
    1.21
    (
    1.18
    er
    1.16
    t
    1.13
    IT
    1.05
    ر
    1.02
    에
    1.01
    an
    0.97
     \
    0.96
    म
    0.95
    Activations Density 0.000%

    No Known Activations