© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3391
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations or groups of people

    oai_token-act-pair · gemini-2.0-flash

    groups

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SOUNDBITE
    -0.53
     незавершена
    -0.49
    PARED
    -0.47
    บรร
    -0.47
    AndEndTag
    -0.46
    asso
    -0.45
    ANZE
    -0.45
    plotly
    -0.45
     intptr
    -0.45
     pr
    -0.44
    POSITIVE LOGITS
     تضيفلها
    0.70
     ویکی‌پدیا
    0.69
     actuels
    0.62
    AutoresizingMask
    0.60
     lèvres
    0.60
    HasForeignKey
    0.59
    tagHelperRunner
    0.57
     scolaires
    0.57
    TargetException
    0.57
     sœurs
    0.57
    Activations Density 12.983%

    No Known Activations