© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124801
    Prev
    Next
    INDEX
    Explanations

    aquabus, aquelarre

    np_acts-logits-general · gemini-2.5-flash-lite

    rare or obscure vocabulary words containing unusual letter sequences, particularly Latin-derived technical terms.

    oai_token-act-pair · claude-4-5-haikuTriggered by @enricobottazzi

    rare or obscure vocabulary

    np_max-act · claude-4-5-haikuTriggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    um
    0.96
     to
    0.95
     Acquisition
    0.92
     Acquisitions
    0.90
    2
    0.89
     acquisition
    0.84
    able
    0.83
    ,
    0.82
    qu
    0.81
    us
    0.80
    POSITIVE LOGITS
    ג
    0.86
     bạn
    0.85
    üşt
    0.79
    ्यावर
    0.79
    ف
    0.77
     gennaio
    0.73
     vutto
    0.73
     judíos
    0.73
    쏟
    0.73
    ج
    0.73
    Activations Density 0.003%

    No Known Activations