© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84949
    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_23_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
     agregar
    0.41
     حج
    0.40
    বলে
    0.39
     бя
    0.39
     फूल
    0.38
    tod
    0.38
    >≥</
    0.37
    ैश
    0.36
    थे
    0.36
    incorpor
    0.36
    POSITIVE LOGITS
    Spart
    0.43
     Spartans
    0.42
     MONEY
    0.40
     ขณะ
    0.39
     inferiority
    0.39
    Italian
    0.39
    しまい
    0.39
    heets
    0.39
    qal
    0.39
    Ln
    0.37
    Activations Density 0.000%

    No Known Activations