© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11278
    Prev
    Next
    INDEX
    Explanations

    phrases related to studies and attention

    oai_token-act-pair · gemini-2.0-flash

    attention

    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
    AddHtmlAttribute
    -0.63
    BufferException
    -0.59
     velkommen
    -0.56
    '}>
    -0.53
    HandlerContext
    -0.52
    følgelig
    -0.52
    giaan
    -0.50
     يتيمه
    -0.50
    nativeElement
    -0.47
     helst
    -0.47
    POSITIVE LOGITS
     AssemblyTitle
    0.63
    __*/
    0.56
     geweldig
    0.52
    ̣ng
    0.52
     intérêt
    0.51
     становника
    0.48
     @"/
    0.48
    Bibliograf
    0.47
     laminar
    0.47
     inadequate
    0.47
    Activations Density 1.292%

    No Known Activations