© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206420
    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_6_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
    ni
    0.96
    is
    0.93
    ards
    0.91
    ens
    0.90
    ను
    0.82
    ри
    0.78
     that
    0.77
    د
    0.77
     so
    0.76
    eding
    0.76
    POSITIVE LOGITS
    لین
    0.88
    бие
    0.82
     Бүгенге
    0.82
    闾
    0.80
     exercitation
    0.79
    ین
    0.79
     Стаўкі
    0.77
    \},
    0.77
     قوانین
    0.77
    cyte
    0.77
    Activations Density 0.000%

    No Known Activations