© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4559
    Prev
    Next
    INDEX
    Explanations

    country names

    oai_token-act-pair · gemini-2.0-flash

    countries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    tagHelperRunner
    -0.74
     Roskov
    -0.74
    ChildScrollView
    -0.67
     ProtoMessage
    -0.63
     متعلقه
    -0.63
     jScrollPane
    -0.63
    RenderAtEndOf
    -0.60
    Referències
    -0.60
    MetaObject
    -0.59
    ScopeManager
    -0.57
    POSITIVE LOGITS
    
    0.79
    <bos>
    0.65
     bivolt
    0.50
     perchance
    0.50
    ukone
    0.49
     prefeitura
    0.48
     region
    0.46
     Occasionally
    0.45
     curves
    0.45
    PyExc
    0.44
    Activations Density 1.505%

    No Known Activations