© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174705
    Prev
    Next
    INDEX
    Explanations

    rest between

    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_20_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
    既
    0.45
    謗
    0.43
    mesinin
    0.43
    each
    0.42
    手工
    0.42
    ants
    0.41
    可知
    0.41
    inya
    0.40
    z
    0.40
    oms
    0.40
    POSITIVE LOGITS
     años
    0.44
     uppercase
    0.44
     année
    0.43
     courtyard
    0.42
     pê
    0.41
    ฟา
    0.40
     Iranian
    0.40
     năm
    0.40
    פו
    0.40
     cephal
    0.40
    Activations Density 0.003%

    No Known Activations