© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39310
    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_3_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
    س
    1.00
    د
    0.89
    ，
    0.83
    ى
    0.82
    ви
    0.75
    да
    0.74
    ي
    0.72
    ి
    0.72
    ،
    0.70
    au
    0.69
    POSITIVE LOGITS
    arın
    0.80
    lara
    0.75
    dle
    0.73
    lice
    0.73
    
    0.72
    :
    0.71
    .
    0.71
    n
    0.70
    ‰
    0.69
    lily
    0.68
    Activations Density 0.000%

    No Known Activations