© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42058
    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_22_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
    an
    0.56
    ان
    0.53
     Translate
    0.53
     Stickers
    0.51
    n
    0.47
     Interface
    0.47
    e
    0.47
     Momentum
    0.46
     Staying
    0.46
    s
    0.46
    POSITIVE LOGITS
     convict
    0.49
     épais
    0.46
     préf
    0.46
     estrés
    0.46
     allongé
    0.44
     ہیں۔
    0.43
     темы
    0.43
    WithFieldContext
    0.43
    GTBase
    0.42
     सहित
    0.41
    Activations Density 0.000%

    No Known Activations