© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215952
    Prev
    Next
    INDEX
    Explanations

    king or ruler

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    リート
    0.43
    üll
    0.43
     photospheres
    0.42
    łym
    0.41
    łon
    0.41
    ifers
    0.40
     пер
    0.38
    屠
    0.38
     jLabel
    0.37
    岑
    0.37
    POSITIVE LOGITS
    رج
    0.82
     رج
    0.79
     राज
    0.64
     Regents
    0.63
    Raj
    0.62
     Regent
    0.62
     reg
    0.61
     Raj
    0.59
     REG
    0.57
    Reg
    0.57
    Activations Density 0.006%

    No Known Activations