© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231388
    Prev
    Next
    INDEX
    Explanations

    complex systems

    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_6_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
    t
    1.05
    ه
    0.88
    ت
    0.88
    س
    0.85
    ار
    0.82
    ل
    0.79
    ۹
    0.76
     oscill
    0.76
    ""
    0.73
    arin
    0.71
    POSITIVE LOGITS
    ки
    1.02
    ли
    1.00
    기
    0.97
    ীয়
    0.93
     habían
    0.89
     tenté
    0.85
    og
    0.84
    śle
    0.83
    ър
    0.83
    국
    0.83
    Activations Density 0.002%

    No Known Activations