© 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. 35867
    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
     nove
    0.62
     apat
    0.62
     quando
    0.59
     ints
    0.59
     nitrite
    0.58
     Attempt
    0.58
     credits
    0.57
     o
    0.56
     scripts
    0.56
     cheio
    0.56
    POSITIVE LOGITS
     وأ
    0.68
     शहरातील
    0.64
     برگزاری
    0.61
    hamdulillah
    0.60
     большей
    0.59
    hamdul
    0.58
    Tại
    0.58
    țile
    0.58
    ເຄື່ອງ
    0.58
     पर्याय
    0.57
    Activations Density 0.000%

    No Known Activations