© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9529
    Prev
    Next
    INDEX
    Explanations

    the word "physical" and words related to programming

    oai_token-act-pair · gemini-2.0-flash

    physical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    arXiv
    -0.69
     genomen
    -0.68
    WriteLiteral
    -0.63
    UIControlState
    -0.59
     diante
    -0.59
     rejoin
    -0.58
     μην
    -0.58
    addGap
    -0.57
     accede
    -0.57
    SequentialGroup
    -0.56
    POSITIVE LOGITS
     NDEBUG
    0.75
     maxn
    0.68
    (:,:,
    0.64
     measurement
    0.63
     Sopho
    0.59
    ivotopis
    0.59
    UDA
    0.59
    anah
    0.59
    soft
    0.58
     Poznań
    0.58
    Activations Density 1.140%

    No Known Activations