© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12723
    Prev
    Next
    INDEX
    Explanations

    numbers with multiple digits, particularly those representing percentages and measurements

    oai_token-act-pair · gemini-2.0-flash

    the number 5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    setVerticalGroup
    -0.82
    thenReturn
    -0.74
    ftagPool
    -0.69
    CodedInputStream
    -0.57
    BagConstraints
    -0.56
    onViewCreated
    -0.56
    AnimationsModule
    -0.54
     onOptions
    -0.54
     recession
    -0.53
    참고
    -0.52
    POSITIVE LOGITS
    znacz
    0.51
    нулась
    0.48
    Παραπομπές
    0.46
     mesurer
    0.44
     measuring
    0.44
     daß
    0.43
    köy
    0.43
    Redaktion
    0.43
     &=&
    0.42
    pente
    0.42
    Activations Density 1.783%

    No Known Activations