© 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. 205925
    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
    ่า
    0.42
    riere
    0.41
    Option
    0.39
    %);
    0.39
    ERP
    0.39
    ̣
    0.39
    intah
    0.37
    set
    0.36
    योग्य
    0.36
    彙
    0.36
    POSITIVE LOGITS
     begged
    0.59
     адво
    0.58
     objected
    0.55
     fences
    0.55
     potatoes
    0.54
     blessings
    0.54
     beggars
    0.53
     empres
    0.53
     swallowed
    0.53
     कटोच
    0.53
    Activations Density 0.000%

    No Known Activations