© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3395
    Prev
    Next
    INDEX
    Explanations

    insects and their relatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    ल
    0.97
    ản
    0.86
    一个
    0.86
    é
    0.86
    сибо
    0.83
    izde
    0.78
    ं
    0.77
    Established
    0.77
    एं
    0.71
    Есть
    0.71
    POSITIVE LOGITS
     insects
    1.21
    िंग
    1.10
    insect
    1.05
    蛉
    1.04
     insect
    1.03
    ,\,\,\,\
    1.03
    蝣
    1.03
    𝓈
    1.01
     beetles
    1.00
    𝙢
    1.00
    Activations Density 0.065%

    No Known Activations