© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87975
    Prev
    Next
    INDEX
    Explanations

    particle accelerator, leaves, leave, wave, Square

    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_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
    و
    0.57
    서는
    0.56
    ص
    0.56
    یر
    0.55
    ವ
    0.55
    먼
    0.55
    фект
    0.52
    ನ
    0.50
    ल
    0.49
     сосре
    0.49
    POSITIVE LOGITS
    an
    0.62
    ed
    0.61
    anzi
    0.61
     Banker
    0.60
     negozio
    0.56
    ad
    0.55
     Wiltshire
    0.54
     Conservative
    0.54
     ここ
    0.54
     winery
    0.54
    Activations Density 0.004%

    No Known Activations