© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207588
    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_19_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
    ли
    0.56
     expertise
    0.47
    ми
    0.47
    し
    0.45
    un
    0.45
    い
    0.44
     industri
    0.43
     proficiency
    0.42
    ي
    0.42
     whine
    0.41
    POSITIVE LOGITS
     Não
    0.54
    astos
    0.51
     عدم
    0.50
     Buddha
    0.49
     Kultur
    0.49
    maßen
    0.48
    statusBar
    0.48
     一个
    0.48
     Ł
    0.47
     목적
    0.47
    Activations Density 0.000%

    No Known Activations