© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45172
    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_13_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
    跺
    0.48
     millioner
    0.47
     zn
    0.46
     dak
    0.46
    k
    0.46
     möj
    0.45
     أر
    0.45
    c
    0.45
     Paglin
    0.45
     befind
    0.45
    POSITIVE LOGITS
    ட்ச
    0.49
     by
    0.47
     они
    0.47
    िसा
    0.45
     которого
    0.44
    今日
    0.43
    irán
    0.42
     она
    0.41
    ческие
    0.41
    ዋል።
    0.41
    Activations Density 0.000%

    No Known Activations