© 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. 42876
    Prev
    Next
    INDEX
    Explanations

    dataclass, @angular

    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
    ᱘
    0.80
     എന്നാൽ
    0.79
     борь
    0.75
     помогает
    0.74
     поможет
    0.74
     божомолу
    0.72
     автомобиля
    0.71
     относятся
    0.71
     появляется
    0.71
     появится
    0.71
    POSITIVE LOGITS
    시
    0.97
    ل
    0.91
    t
    0.82
    ق
    0.79
    ם
    0.79
    리
    0.77
    هم
    0.75
    지
    0.73
    ת
    0.73
    ب
    0.72
    Activations Density 0.002%

    No Known Activations