© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192790
    Prev
    Next
    INDEX
    Explanations

    vietnam

    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_4_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
    ↵
    1.00
     contagion
    0.78
    </h2>
    0.72
    </td>
    0.71
    </b>
    0.71
    ).
    0.70
    ↵↵
    0.69
    ↵↵↵
    0.69
    </i>
    0.68
    </h3>
    0.67
    POSITIVE LOGITS
    (
    1.05
    ની
    1.00
    aj
    0.99
    håll
    0.99
    주
    0.98
    ای
    0.93
    માં
    0.93
    Taiwan
    0.92
    ડ
    0.91
    し
    0.89
    Activations Density 0.000%

    No Known Activations