© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13454
    Prev
    Next
    INDEX
    Explanations

    places where shopping and dining occur

    oai_token-act-pair · gemini-2.0-flash

    courts

    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
    Negative Logits
    <bos>
    -0.57
    dė
    -0.54
     spē
    -0.54
    znacz
    -0.52
     förs
    -0.51
    Rè
    -0.50
    ussch
    -0.49
    nical
    -0.49
    Use
    -0.49
     sprá
    -0.48
    POSITIVE LOGITS
    جوايز
    0.82
    TestingModule
    0.71
    makeText
    0.69
    rophoresis
    0.68
    providedIn
    0.62
     AssemblyCompany
    0.61
    TemporalType
    0.60
     JMenuItem
    0.60
     AutoMapper
    0.60
     فريبيس
    0.59
    Activations Density 1.303%

    No Known Activations