© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16201
    Prev
    Next
    INDEX
    Explanations

    words and phrases that could be used to support an argument

    oai_token-act-pair · gemini-2.0-flash

    Origins and ownership

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     HasFactory
    -0.93
    offsetof
    -0.85
     AssemblyTitle
    -0.84
    GEBURTSDATUM
    -0.81
    initComponents
    -0.79
     Roskov
    -0.79
    paksa
    -0.79
     مواليد
    -0.77
    ंदीखरीदारी
    -0.74
    ThroughAttribute
    -0.73
    POSITIVE LOGITS
     any
    0.48
     Mar
    0.44
     it
    0.43
     em
    0.41
     the
    0.41
     mer
    0.40
    .
    0.39
     mar
    0.39
     ways
    0.39
     if
    0.39
    Activations Density 16.541%

    No Known Activations