© 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. 113146
    Prev
    Next
    INDEX
    Explanations

    wobbled

    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_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
    \
    1.54
    im
    1.28
    una
    1.21
    unam
    0.98
     that
    0.97
     a
    0.95
    人
    0.95
    se
    0.93
    ના
    0.91
     is
    0.91
    POSITIVE LOGITS
    ৫
    1.11
    ebabkan
    1.09
     ajout
    1.06
     entend
    1.05
     cambi
    1.05
    ле
    1.02
     effectuées
    1.02
    т
    1.02
     ouv
    1.00
    ศ์
    0.97
    Activations Density 0.000%

    No Known Activations