© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229676
    Prev
    Next
    INDEX
    Explanations

    for-profit and not-for-profit entities

    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
    p
    1.18
    n
    0.96
    ne
    0.94
    на
    0.93
    ized
    0.93
     FYI
    0.93
    x
    0.93
    ara
    0.92
     other
    0.89
    ed
    0.89
    POSITIVE LOGITS
    ו
    1.49
    ם
    1.05
    ت
    0.98
    و
    0.96
    دس
    0.93
    ر
    0.91
    ווע
    0.90
    س
    0.89
    ра
    0.89
    مي
    0.89
    Activations Density 0.000%

    No Known Activations