© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15255
    Prev
    Next
    INDEX
    Explanations

    words that show support (for an idea or concept) or connection.

    oai_token-act-pair · gemini-2.0-flash

    Formal arguments and evidence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     autorytatywna
    -0.93
     Италијани
    -0.88
    GenerationType
    -0.85
     AssemblyProduct
    -0.75
     Савезне
    -0.74
     дописавши
    -0.73
    ftagPool
    -0.71
    AndEndTag
    -0.71
    asteroide
    -0.70
    InSection
    -0.69
    POSITIVE LOGITS
    yntaxException
    0.55
     surprising
    0.50
    é
    0.47
     unexpected
    0.44
     inf
    0.43
     unusual
    0.43
    ig
    0.42
     meaning
    0.42
     few
    0.41
     Gar
    0.41
    Activations Density 6.193%

    No Known Activations