© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15175
    Prev
    Next
    INDEX
    Explanations

    first president, king, minister

    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_15_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
    o
    0.42
     Poul
    0.41
     Kan
    0.38
    До
    0.37
    Н
    0.36
     Moody
    0.35
     రోజు
    0.35
    Когда
    0.35
    ське
    0.34
    Как
    0.33
    POSITIVE LOGITS
    齒
    0.36
     accidentally
    0.33
     such
    0.33
     deemed
    0.33
    ціона
    0.32
     алфа
    0.32
     ofthe
    0.31
    這種
    0.31
     CAROLINA
    0.31
    :\
    0.30
    Activations Density 0.052%

    No Known Activations