© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197553
    Prev
    Next
    INDEX
    Explanations

    legal or government entities and locations

    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_27_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
    ర్చి
    0.29
    ith
    0.29
     recognisable
    0.28
     thêm
    0.28
     alterar
    0.27
    />
    0.27
    allergenic
    0.27
    >$
    0.27
     aliqua
    0.27
     hives
    0.27
    POSITIVE LOGITS
     souci
    0.30
     пропа
    0.29
     comport
    0.29
     Board
    0.28
    图形
    0.28
    先前
    0.28
     preocupaciones
    0.28
    道具
    0.27
    法院
    0.27
    وجوان
    0.27
    Activations Density 0.000%

    No Known Activations