© 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
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 90789
    Prev
    Next
    INDEX
    Explanations

    header guard

    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
     пой
    0.57
    да
    0.56
    antiation
    0.55
     ۽
    0.55
    ும்போது
    0.54
    ewell
    0.53
    ень
    0.49
     regularmente
    0.49
    efeuille
    0.49
    ifica
    0.48
    POSITIVE LOGITS
     밝혔
    0.59
    '};
    0.57
    keyCode
    0.57
     McGuire
    0.56
     with
    0.55
    ];
    0.54
    ]");
    0.54
    }');
    0.54
    '];
    0.53
    ICE
    0.53
    Activations Density 0.002%

    No Known Activations