© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127141
    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_3_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
    كل
    0.68
    জ
    0.68
    は
    0.67
    r
    0.64
    াল
    0.62
     alquiler
    0.61
    是谁
    0.61
    מ
    0.61
     Miet
    0.60
    أي
    0.60
    POSITIVE LOGITS
    า
    0.77
    aha
    0.62
    have
    0.61
    वर्ती
    0.60
    들이
    0.59
     laughing
    0.57
    appers
    0.57
    ものは
    0.56
    aks
    0.55
    mouth
    0.54
    Activations Density 0.000%

    No Known Activations