© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 239740
    Prev
    Next
    INDEX
    Explanations

    alighting on golden fields

    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_25_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
     Actually
    0.30
     Cuisine
    0.29
    符号
    0.28
     😄
    0.27
    deleteAll
    0.26
     arreg
    0.26
    কো
    0.25
     Jeans
    0.25
    漉
    0.25
    挑戦
    0.25
    POSITIVE LOGITS
     elasticity
    0.34
     considering
    0.29
     zmian
    0.29
     considerato
    0.29
    한다
    0.28
    elastic
    0.27
    iete
    0.27
    cèle
    0.27
    skjaer
    0.27
    considering
    0.26
    Activations Density 0.031%

    No Known Activations