© 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. 88266
    Prev
    Next
    INDEX
    Explanations

    op followed by punctuation

    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
    ۔
    1.01
    ።
    0.94
    ي
    0.89
    。
    0.84
     angered
    0.78
     sprinter
    0.74
    ৭
    0.73
     helmet
    0.73
     modelo
    0.72
    د
    0.72
    POSITIVE LOGITS
    2
    0.86
    ための
    0.73
    rj
    0.72
    all
    0.71
    ges
    0.69
    a
    0.64
    führung
    0.62
    cipl
    0.59
    flakes
    0.59
    ;
    0.59
    Activations Density 0.000%

    No Known Activations