© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1523
    Prev
    Next
    INDEX
    Explanations

    technical writing including the articles 'a' and 'an', numbers, and words such as 'layer', 'part', and 'direction.'

    oai_token-act-pair · gemini-2.0-flash

    a

    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
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.75
     AssemblyTitle
    -0.73
    Mutagenicity
    -0.71
    WriteAttribute
    -0.70
    abestanden
    -0.68
    ----</
    -0.67
    claimer
    -0.66
     CreateTagHelper
    -0.64
    存于互联网档案馆
    -0.63
    TagMode
    -0.63
    POSITIVE LOGITS
    แต่
    0.51
    ">'.$
    0.49
     détaillée
    0.48
    тику
    0.47
    cinia
    0.46
    kennt
    0.45
     Knot
    0.45
    IUrlHelper
    0.43
     \#
    0.43
    stwo
    0.43
    Activations Density 4.716%

    No Known Activations