© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13131
    Prev
    Next
    INDEX
    Explanations

    words related to creating/building/composing something

    oai_token-act-pair · gemini-2.0-flash

    composition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     composition
    -2.75
     Composition
    -2.48
    composition
    -2.38
    Composition
    -2.36
     compositions
    -2.20
     COMPOSITION
    -2.13
     composed
    -1.89
     composición
    -1.89
     composizione
    -1.79
    COMPOSITION
    -1.79
    POSITIVE LOGITS
    Datuak
    0.70
     Paglinawan
    0.65
    /*
    0.65
    __)
    0.57
    batore
    0.54
    HostException
    0.52
    ImageIO
    0.52
    ConstraintMaker
    0.51
    ніципа
    0.51
     оригіналу
    0.51
    Activations Density 2.058%

    No Known Activations