© 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. 206475
    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_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
     불구하고
    1.10
    이었
    0.84
    ድግዳ
    0.84
     alimentaires
    0.84
    \}.
    0.80
     влияния
    0.78
     Что
    0.77
    pleasant
    0.77
     писа
    0.76
    люб
    0.76
    POSITIVE LOGITS
     be
    1.10
    ER
    1.10
    ad
    1.08
    （
    1.04
    ta
    1.01
    with
    1.00
    on
    0.99
     as
    0.99
    were
    0.99
    ラ
    0.99
    Activations Density 0.000%

    No Known Activations