© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8225
    Prev
    Next
    INDEX
    Explanations

    uses of the verb *compose* along with other verbs indicating focus or intention

    oai_token-act-pair · gemini-2.0-flash

    almost

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    TagHelper
    -0.62
    DoubleQuotes
    -0.60
    InBackground
    -0.53
    Affiliations
    -0.50
    AlterField
    -0.50
     않습니다
    -0.50
    RegistryLite
    -0.49
    כשיו
    -0.49
     um
    -0.49
    Datuak
    -0.48
    POSITIVE LOGITS
     almost
    0.97
    almost
    0.94
    Almost
    0.91
     Almost
    0.87
     entirely
    0.75
    entire
    0.63
     quase
    0.63
    بوابة
    0.62
     presque
    0.62
    sole
    0.57
    Activations Density 3.329%

    No Known Activations