© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35783
    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_11_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
     कर्तव्य
    0.64
    inę
    0.61
    ,}$
    0.59
    🥐
    0.56
    lą
    0.56
     swoją
    0.56
     Siles
    0.56
     będzie
    0.55
     offend
    0.55
    ńskiego
    0.55
    POSITIVE LOGITS
    ClO
    0.59
     förm
    0.54
     StringIO
    0.52
     polarity
    0.51
    dU
    0.50
    :</
    0.49
     ‍
    0.49
     Generating
    0.49
    Д
    0.47
     polar
    0.47
    Activations Density 0.000%

    No Known Activations