© 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
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 43917
    Prev
    Next
    INDEX
    Explanations

    Starship, Jetson Nano, Junos Space

    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
    ون
    0.77
    l
    0.72
    ль
    0.70
    ό
    0.68
    ले
    0.68
    getAbsolutePath
    0.68
    ل
    0.68
    ली
    0.66
    est
    0.66
    انی
    0.65
    POSITIVE LOGITS
     subdue
    0.73
    ores
    0.68
    <0x0D>
    0.68
    ী
    0.68
     vary
    0.67
    า
    0.67
     have
    0.66
    ,
    0.64
    </td>
    0.64
     bạn
    0.63
    Activations Density 0.001%

    No Known Activations