© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207235
    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_56_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
     oficinas
    0.42
     passada
    0.42
     Near
    0.40
     vijj
    0.40
    Ꮴ
    0.40
     eliminación
    0.39
     Vitor
    0.38
     cercana
    0.38
     próxima
    0.38
     próximos
    0.38
    POSITIVE LOGITS
    ..
    0.41
    stwa
    0.41
    نگ
    0.40
    y
    0.40
    ,,
    0.38
    ệp
    0.37
    yip
    0.37
    te
    0.37
    coat
    0.37
     ن
    0.37
    Activations Density 0.000%

    No Known Activations