© 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. 222205
    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
    ब्स
    0.47
    าร์
    0.46
    ometraje
    0.46
    까
    0.46
    <0xBE>
    0.44
    颼
    0.43
     ActionListener
    0.43
    <0x92>
    0.42
    ાર્થી
    0.42
    <0x82>
    0.42
    POSITIVE LOGITS
     new
    0.52
    Forest
    0.50
    Ram
    0.50
    Princ
    0.50
     life
    0.48
     Ram
    0.48
     co
    0.47
    1
    0.47
     dissu
    0.46
     caries
    0.46
    Activations Density 0.000%

    No Known Activations