© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39255
    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
    Ts
    0.48
    IN
    0.47
    M
    0.47
    Termination
    0.46
    NN
    0.45
    Z
    0.44
    ID
    0.44
    OL
    0.44
    h
    0.44
    ㏄
    0.44
    POSITIVE LOGITS
     कॉले
    0.50
     lewat
    0.50
     mùa
    0.49
     клини
    0.49
     przez
    0.47
     oczywiście
    0.47
     diseño
    0.47
     শীত
    0.47
     livelli
    0.47
     chào
    0.46
    Activations Density 0.000%

    No Known Activations