© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166725
    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_31_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
    alir
    0.41
    ―
    0.39
    raquo
    0.38
    yczny
    0.38
    ϟ
    0.38
     parlour
    0.36
    kk
    0.36
    кое
    0.36
     proximate
    0.36
     erz
    0.35
    POSITIVE LOGITS
     Tài
    0.40
     cu
    0.36
     தொடர்பு
    0.36
     cannot
    0.35
     Reef
    0.35
     langage
    0.34
     knowing
    0.34
     Hull
    0.34
    запа
    0.34
     宋
    0.34
    Activations Density 0.000%

    No Known Activations