© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161262
    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_2_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
    い
    0.66
    ę
    0.65
    ı
    0.61
    सा
    0.59
    ys
    0.57
    िस
    0.57
    وم
    0.57
    3
    0.57
    ী
    0.56
    ne
    0.55
    POSITIVE LOGITS
    го
    0.77
    al
    0.61
     as
    0.60
    也
    0.55
    은
    0.55
    ής
    0.55
    กลาง
    0.52
     aswell
    0.52
    টি
    0.52
    ﺀ
    0.51
    Activations Density 0.000%

    No Known Activations