© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50240
    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_10_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
    à
    0.74
    ل
    0.69
    omores
    0.68
    е
    0.66
    ке
    0.64
    لل
    0.64
    ି
    0.64
    ètres
    0.64
    ной
    0.63
    яна
    0.63
    POSITIVE LOGITS
    :
    0.80
     in
    0.79
     samoglas
    0.75
    ية
    0.75
     Didn
    0.68
    ↵↵
    0.66
     Observing
    0.63
     Presidency
    0.61
    gäng
    0.61
     overly
    0.60
    Activations Density 0.000%

    No Known Activations