© 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. 11664
    Prev
    Next
    INDEX
    Explanations

    the word "press", especially when followed by the name of a key or button

    oai_token-act-pair · gemini-2.0-flash

    press

    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
     ainfi
    -0.75
     colspan
    -0.73
     CHAPITRE
    -0.67
    criture
    -0.66
    новништво
    -0.64
     Paglinawan
    -0.63
    jgl
    -0.62
     auffi
    -0.61
     dévelo
    -0.59
    ModelSerializer
    -0.59
    POSITIVE LOGITS
     happening
    0.68
     defunct
    0.65
    cially
    0.61
     realising
    0.60
    omato
    0.60
     dangerously
    0.60
    {}/
    0.60
    mied
    0.59
     famously
    0.59
     demurrer
    0.57
    Activations Density 1.405%

    No Known Activations