© 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. 57597
    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
    대가
    0.66
     thefts
    0.61
     histórias
    0.56
    大手
    0.56
    ))))
    0.55
     quantifier
    0.54
     প্রতার
    0.54
    ラ
    0.53
     brownies
    0.53
    RATE
    0.52
    POSITIVE LOGITS
    a
    0.60
    Fernseh
    0.55
     başkan
    0.54
    ssh
    0.53
    iß
    0.52
    its
    0.51
    akte
    0.51
    影视
    0.51
    Ahmed
    0.51
    akt
    0.50
    Activations Density 0.004%

    No Known Activations