© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211764
    Prev
    Next
    INDEX
    Explanations

    balcony, ies, ics, con

    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_5_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
    ;
    1.26
    ج
    1.07
    ER
    1.02
    il
    0.98
    r
    0.98
     emocion
    0.88
    며
    0.87
     Soyuz
    0.85
    )$.
    0.82
     люди
    0.82
    POSITIVE LOGITS
    at
    1.43
    로
    1.23
    و
    1.13
    มัน
    1.02
    д
    1.01
    ？」
    1.00
    ב
    0.99
    ו
    0.94
    י
    0.92
    ？”
    0.91
    Activations Density 0.000%

    No Known Activations