© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 145394
    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_0_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
    。『
    0.61
    <unused187>
    0.57
    妑
    0.55
     Gö
    0.54
     التالية
    0.54
    ்ப்ப
    0.54
    .‏
    0.51
    <unused108>
    0.51
    <unused574>
    0.51
     〢
    0.50
    POSITIVE LOGITS
     not
    0.58
    make
    0.55
    you
    0.54
    not
    0.52
    market
    0.52
    ot
    0.50
    ownership
    0.50
    define
    0.49
     market
    0.49
    normal
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.