© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140458
    Prev
    Next
    INDEX
    Explanations

    forms of "to be"

    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_12_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
    اة
    0.65
    amientos
    0.61
     lymphatiques
    0.59
    écran
    0.59
    汅
    0.59
    <unused636>
    0.59
    enty
    0.58
    смотрим
    0.58
     بیاکتنې
    0.58
    <unused580>
    0.58
    POSITIVE LOGITS
    );
    0.70
    ల
    0.57
    ↵
    0.52
    ก่
    0.52
     la
    0.51
    };
    0.50
    g
    0.50
    )
    0.50
     $
    0.48
    也
    0.48
    Activations Density 0.013%

    No Known Activations