© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195784
    Prev
    Next
    INDEX
    Explanations

    input prompt

    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_26_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
     download
    0.38
    s
    0.38
     set
    0.37
    there
    0.37
    yor
    0.36
    download
    0.35
     therein
    0.35
    ماع
    0.34
     firepower
    0.34
    yue
    0.34
    POSITIVE LOGITS
     купи
    0.46
     구매
    0.44
     ဘ
    0.42
     больше
    0.41
    оні
    0.40
     于
    0.39
    PROPERTY
    0.38
     kø
    0.38
     comprar
    0.38
     kö
    0.38
    Activations Density 0.000%

    No Known Activations