© 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. 195047
    Prev
    Next
    INDEX
    Explanations

    websites and media

    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
    idy
    0.43
    iglas
    0.43
    sid
    0.42
    isf
    0.40
    pol
    0.39
     Redd
    0.37
    阳
    0.37
     Yang
    0.37
    WebGL
    0.37
    Yang
    0.37
    POSITIVE LOGITS
     fontSize
    0.41
     fontsize
    0.41
    Frances
    0.40
    एंड
    0.39
    Joel
    0.39
    То
    0.38
    зара
    0.38
     Francesca
    0.38
     Е
    0.37
    JOHN
    0.37
    Activations Density 0.002%

    No Known Activations