© 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. 3018
    Prev
    Next
    INDEX
    Explanations

    fractions and the word "Razor"

    oai_token-act-pair · gemini-2.0-flash

    categories/distinctions

    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
     houſe
    -0.85
    LLocation
    -0.77
     Jefus
    -0.77
     ſever
    -0.76
     purpoſe
    -0.74
    iffance
    -0.73
     faſt
    -0.72
     pleaſure
    -0.72
     ſen
    -0.71
    extAlignment
    -0.70
    POSITIVE LOGITS
     the
    0.64
    <blockquote>
    0.59
     a
    0.56
     my
    0.52
     his
    0.52
     him
    0.52
     CWE
    0.50
    parency
    0.45
    /**
    0.45
    ього
    0.45
    Activations Density 0.833%

    No Known Activations