© 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-2-2B
    3. 12-GEMMASCOPE-TRANSCODER-16K
    4. 11355
    Prev
    Next
    INDEX
    Explanations

    phrases involving inequalities, generally in the context of medical or scientific measurements

    oai_token-act-pair · gemini-2.0-flash

    comparisons and measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     للمعارف
    -0.56
     متعلقه
    -0.56
    ViewFeatures
    -0.47
     connexes
    -0.46
     שוליים
    -0.46
     صوتيه
    -0.46
    ynki
    -0.45
     gebraucht
    -0.44
     getIs
    -0.43
    atimes
    -0.43
    POSITIVE LOGITS
    aarrggbb
    0.68
    RegistryLite
    0.66
    minecraftforge
    0.65
     EconPapers
    0.61
     infection
    0.56
     ?>>
    0.56
    URLException
    0.56
    MigrationBuilder
    0.55
     moh
    0.53
    __':
    
    0.53
    Activations Density 0.753%

    No Known Activations