© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57055
    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_11_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
     alloc
    0.58
     трак
    0.55
     matrícula
    0.53
    ၈
    0.51
     allocation
    0.51
     glab
    0.51
     minced
    0.50
     석
    0.49
     fuente
    0.49
     phenotypic
    0.48
    POSITIVE LOGITS
     Something
    0.49
     Eyes
    0.48
     Nationals
    0.46
    vora
    0.46
     Tours
    0.46
     President
    0.45
     Corporation
    0.45
     Corporal
    0.45
     Circuit
    0.44
     Corps
    0.44
    Activations Density 0.000%

    No Known Activations