© 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. 40134
    Prev
    Next
    INDEX
    Explanations

    python imports

    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
    ره
    0.52
    FileCopy
    0.52
     экономических
    0.52
     noteworthy
    0.51
    нер
    0.50
     применяется
    0.50
    瑆
    0.49
    sta
    0.48
     крупных
    0.48
     artículo
    0.47
    POSITIVE LOGITS
     that
    0.59
    ність
    0.57
    }$$
    0.56
    rän
    0.56
     konstant
    0.54
    olazione
    0.54
    ട്ടില്ല
    0.54
    ーフ
    0.52
     konkur
    0.52
     कोस
    0.52
    Activations Density 0.001%

    No Known Activations