© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 232659
    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_46_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
    Really
    0.48
    really
    0.42
     Really
    0.41
    河
    0.41
    Joining
    0.39
     joining
    0.39
     Joining
    0.38
     really
    0.38
     vraiment
    0.38
     joins
    0.37
    POSITIVE LOGITS
    books
    0.44
    ফেট
    0.41
    াস্ত
    0.39
     አስ
    0.38
    絖
    0.38
     کئے
    0.38
    鰓
    0.38
    ওয়্যার
    0.37
    कात
    0.36
     ਕੀ
    0.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.