© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85187
    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_23_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
     মিনিট
    0.41
     어린
    0.40
    ToArabic
    0.40
     আবাসিক
    0.40
    ระดับ
    0.39
    𝗳
    0.39
     }}\
    0.37
     ტი
    0.37
    TrackAngle
    0.37
    
    0.37
    POSITIVE LOGITS
    #
    0.41
    owing
    0.40
    Product
    0.40
    Multiple
    0.39
    Citizen
    0.38
    نز
    0.38
    Boris
    0.38
    Meth
    0.38
     protéger
    0.38
    Bour
    0.38
    Activations Density 0.000%

    No Known Activations