© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89083
    Prev
    Next
    INDEX
    Explanations

    following, 之后

    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
    that
    0.70
     ত
    0.66
     завод
    0.64
     ");
    0.63
     പക്ഷേ
    0.63
     POSSIBLE
    0.62
     सम्बन्ध
    0.62
    --");
    0.61
     வெளியே
    0.60
     STORY
    0.60
    POSITIVE LOGITS
    ed
    0.95
    ing
    0.90
    ا
    0.79
    ने
    0.77
    ా
    0.69
    为例
    0.68
    ில்
    0.68
    ين
    0.65
    u
    0.65
    َا
    0.64
    Activations Density 0.000%

    No Known Activations