© 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. 171679
    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
     puncak
    0.54
    ันทร์
    0.53
    湟
    0.51
    ੰਜ
    0.50
     réflex
    0.48
     tingkat
    0.47
     kendaraan
    0.47
    രുദ്ധ
    0.47
    ისუფ
    0.46
     pelayanan
    0.46
    POSITIVE LOGITS
    t
    0.48
    #
    0.45
    usually
    0.44
    Generally
    0.43
    rounded
    0.43
    sentence
    0.43
    u
    0.43
    ures
    0.43
    ？
    0.42
    label
    0.42
    Activations Density 0.000%

    No Known Activations