© 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. 258541
    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
    ängen
    0.40
    ënten
    0.39
    ێر
    0.39
    仕
    0.38
    Flair
    0.38
     Angew
    0.37
     встроен
    0.37
    ύν
    0.36
     handyman
    0.36
    ὥ
    0.36
    POSITIVE LOGITS
    regnum
    0.45
    productId
    0.41
    sector
    0.41
    dumps
    0.41
     ابي
    0.40
    fd
    0.40
    ຜະລິດຕ
    0.40
     राज्य
    0.39
     evaporates
    0.39
     державного
    0.38
    Activations Density 0.000%

    No Known Activations