© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211426
    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_20_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
    sectional
    0.50
    ברה
    0.50
    钱包
    0.49
    轰
    0.46
    cosity
    0.45
     tốc
    0.44
     скорость
    0.44
    paralleled
    0.43
    塁
    0.43
    ersion
    0.43
    POSITIVE LOGITS
     पाओ
    0.50
     sheen
    0.50
    ఇ
    0.50
     Fr
    0.48
                
    0.48
     Vamos
    0.48
     reservations
    0.47
     Government
    0.47
    GET
    0.47
     renderings
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.