© 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. 202155
    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
     terdapat
    1.09
     by
    1.04
     are
    0.98
     są
    0.95
     vuole
    0.94
     gusto
    0.92
    j
    0.92
     were
    0.91
    izi
    0.90
    \
    0.89
    POSITIVE LOGITS
    ↵
    1.04
    트
    0.97
    త్య
    0.97
    տ
    0.94
    وت
    0.93
    ták
    0.93
    тах
    0.90
    지
    0.90
    కు
    0.89
    其他的
    0.89
    Activations Density 0.000%

    No Known Activations