© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39482
    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_11_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
    0.48
     bouquet
    0.43
    z
    0.41
    <0xA8>
    0.41
    วาง
    0.40
    -
    0.40
     לאחר
    0.39
     tear
    0.39
     linen
    0.38
     الاد
    0.38
    POSITIVE LOGITS
     Пан
    0.51
    АР
    0.49
     bandits
    0.49
     mercenaries
    0.48
     осе
    0.48
    뷁
    0.48
     Breeders
    0.48
    蛻
    0.47
     OXIDES
    0.47
    ㌔
    0.47
    Activations Density 0.000%

    No Known Activations