© 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. 133615
    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_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
     legitimate
    0.43
     legitim
    0.38
      
    0.37
     Social
    0.36
     Commanders
    0.36
     মুজিবের
    0.36
    \-
    0.36
     White
    0.35
     Madrid
    0.35
     legit
    0.35
    POSITIVE LOGITS
    arlock
    0.42
    uxe
    0.41
     என்னுடைய
    0.41
     хочется
    0.40
    দুর
    0.39
     которыми
    0.39
     पन
    0.39
    ={<
    0.38
    chequer
    0.38
    āra
    0.38
    Activations Density 0.000%

    No Known Activations