© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44970
    Prev
    Next
    INDEX
    Explanations

    patient care

    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_13_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
    ing
    0.52
    لى
    0.50
    ición
    0.50
    ۳
    0.50
    lı
    0.49
    ة
    0.49
    áno
    0.49
    伉
    0.49
    anium
    0.48
    Глав
    0.48
    POSITIVE LOGITS
     potest
    0.52
    ).”
    0.49
    )”.
    0.49
    浠
    0.48
    )
    0.47
    )".
    0.46
    people
    0.46
    )."
    0.45
     Nationen
    0.45
     formatter
    0.44
    Activations Density 0.068%

    No Known Activations