© 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. 25567
    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
     permeability
    0.50
     &:
    0.48
    //}
    0.47
    >());
    0.47
     coat
    0.46
     par
    0.46
     cal
    0.45
     phon
    0.45
    하고
    0.45
     doublet
    0.44
    POSITIVE LOGITS
    ের
    0.60
    𝓈
    0.56
     snee
    0.54
    ים
    0.53
    मैन
    0.51
    wyr
    0.51
     Ле
    0.50
     खबरें
    0.50
     Cheesecake
    0.50
    َات
    0.50
    Activations Density 0.000%

    No Known Activations