© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138589
    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_37_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
    መ
    0.39
    पंथी
    0.39
     im
    0.37
    extrem
    0.37
     Collections
    0.37
     평균
    0.37
     والدہ
    0.37
     과정
    0.36
    blich
    0.36
    由
    0.36
    POSITIVE LOGITS
     inked
    0.40
    OMET
    0.37
     pilotos
    0.36
     unica
    0.36
    UNIC
    0.34
     Palace
    0.34
     நடத்து
    0.33
     Georges
    0.33
     precedents
    0.33
    inko
    0.33
    Activations Density 0.000%

    No Known Activations