© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61755
    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_2_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
    ۳
    1.14
    3
    1.08
    ഊ
    1.03
    もら
    1.01
     bombé
    0.98
     suhu
    0.98
    gahan
    0.95
    nimi
    0.95
     invern
    0.94
     prisión
    0.93
    POSITIVE LOGITS
    л
    1.30
    ו
    1.08
                  
    1.05
    س
    1.00
    on
    0.94
    న
    0.93
    ى
    0.92
    (
    0.91
    s
    0.90
    ات
    0.90
    Activations Density 0.000%

    No Known Activations