© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44407
    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_13_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
     U
    0.55
    يا
    0.50
     L
    0.49
    ρα
    0.48
    ens
    0.47
    اهد
    0.46
    ボ
    0.46
    ڏ
    0.45
     Ben
    0.44
    ستخدم
    0.44
    POSITIVE LOGITS
     سیک
    0.55
    idcoin
    0.50
     була
    0.49
     ordination
    0.48
     꼭
    0.48
     recognises
    0.47
    concrete
    0.46
     stratification
    0.46
     горо
    0.46
    LoginPage
    0.46
    Activations Density 0.000%

    No Known Activations