© 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. 170708
    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
    stage
    0.48
     الأكثر
    0.46
    ṟ
    0.45
     çalışan
    0.44
    Xem
    0.44
     أكثر
    0.44
    țele
    0.44
    Nas
    0.43
     κινη
    0.43
    șt
    0.43
    POSITIVE LOGITS
    ب
    0.50
     উপজে
    0.47
    บ
    0.44
    <
    0.43
     discret
    0.42
    ゲット
    0.42
     hectares
    0.41
    یو
    0.41
    所得
    0.41
     banal
    0.40
    Activations Density 0.000%

    No Known Activations