© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133708
    Prev
    Next
    INDEX
    Explanations

    byproducts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    kannya
    1.00
     theses
    0.98
    r
    0.94
     internalization
    0.92
    n
    0.91
    7
    0.91
    k
    0.91
     enlist
    0.90
     inventories
    0.90
     núcle
    0.88
    POSITIVE LOGITS
    ص
    1.26
    apping
    0.89
     They
    0.86
    定了
    0.81
    ่
    0.81
    ία
    0.80
    خ
    0.80
     REIT
    0.80
    ف
    0.80
     powied
    0.79
    Activations Density 0.000%

    No Known Activations