© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35578
    Prev
    Next
    INDEX
    Explanations

    **Park**, **burg**, **et** suffixes

    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_11_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
    \\
    0.16
     by
    0.15
    TS
    0.14
    我
    0.14
     brighter
    0.14
     apporter
    0.13
     état
    0.13
    పూ
    0.13
    TH
    0.13
     ảnh
    0.13
    POSITIVE LOGITS
     เด
    0.16
    <unused266>
    0.16
    ra
    0.16
    rera
    0.15
    ബരി
    0.15
    प्शन
    0.15
     حتی
    0.15
    mazione
    0.15
    Ketika
    0.15
     Коро
    0.15
    Activations Density 0.002%

    No Known Activations