© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8553
    Prev
    Next
    INDEX
    Explanations

    a wide variety of common words and phrases without an obvious theme

    oai_token-act-pair · gemini-2.0-flash

    Introductions/Naming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     CreateTagHelper
    -0.57
    antiation
    -0.47
     Loreto
    -0.42
     Asian
    -0.42
     BRE
    -0.41
     SEC
    -0.41
    makeConstraints
    -0.41
    wein
    -0.40
    enderror
    -0.40
    WritableDatabase
    -0.40
    POSITIVE LOGITS
    GEBURTSDATUM
    0.88
    SourceChecksum
    0.68
    popularity
    0.66
     Mr
    0.66
    Mr
    0.65
    Дереккөздер
    0.64
    xase
    0.62
     Италијани
    0.61
    LookAnd
    0.61
    cloudfront
    0.61
    Activations Density 2.640%

    No Known Activations