© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120809
    Prev
    Next
    INDEX
    Explanations

    The neuron detects sequences where a quantity increases or decreases, often related to size or frequency

    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
     ashore
    0.40
    改变
    0.38
     exaggerated
    0.38
    etze
    0.38
     medicines
    0.38
     severally
    0.38
    귄
    0.37
    atuan
    0.36
    ateri
    0.36
     exaggerate
    0.35
    POSITIVE LOGITS
    invisible
    0.44
    銃
    0.43
     पुष्प
    0.40
    किसान
    0.40
     согласно
    0.39
    जैसे
    0.39
     مست
    0.38
     WORKING
    0.38
     статью
    0.38
    佼
    0.38
    Activations Density 0.003%

    No Known Activations