© 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. 205449
    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
    -
    1.27
     is
    1.23
    ↵↵
    1.21
    ’
    1.19
    a
    1.15
    ه
    1.13
    ה
    1.05
    3
    1.01
    5
    1.01
    瑞
    0.97
    POSITIVE LOGITS
    𝐚
    0.96
     αλλά
    0.95
     fiestas
    0.91
     quedaría
    0.91
    It
    0.90
    есть
    0.89
     QSOs
    0.89
     duckys
    0.88
     apprentices
    0.87
    𝕕
    0.87
    Activations Density 0.000%

    No Known Activations