© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226420
    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_10_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
     Cantonese
    0.48
     determined
    0.47
     g
    0.44
     slower
    0.43
     l
    0.43
     Amino
    0.43
     melanoma
    0.42
     Warrant
    0.42
     Determined
    0.42
    horn
    0.41
    POSITIVE LOGITS
    ى
    0.55
    to
    0.55
    博
    0.51
    脿
    0.51
    בית
    0.50
     cultivo
    0.50
     była
    0.50
     modul
    0.49
    Dialog
    0.49
    iativa
    0.48
    Activations Density 0.000%

    No Known Activations