© 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. 215564
    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
     Fiber
    0.40
     Inet
    0.37
    ichert
    0.36
     Networking
    0.36
     Netzwerk
    0.35
    蜈
    0.34
     ಚ
    0.34
    ၡ
    0.33
     livelihood
    0.33
    antiation
    0.33
    POSITIVE LOGITS
    "}
    0.36
    köz
    0.34
    兵
    0.33
    规则
    0.32
    "}}
    0.32
    upani
    0.32
    Yep
    0.31
    юм
    0.31
     규칙
    0.31
    "))
    0.31
    Activations Density 0.000%

    No Known Activations