© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88637
    Prev
    Next
    INDEX
    Explanations

    context manager

    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_3_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
    '
    0.66
    interaction
    0.65
    connector
    0.62
    future
    0.60
    هيل
    0.59
    طنين
    0.59
    মিস্ট
    0.57
    headlines
    0.57
    context
    0.57
     futuro
    0.57
    POSITIVE LOGITS
    ā
    0.64
    к
    0.60
    ล
    0.57
    ै
    0.57
    브
    0.57
    ulação
    0.54
    deo
    0.53
    ä
    0.53
    };
    0.52
    æ
    0.52
    Activations Density 0.002%

    No Known Activations