© 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. 8327
    Prev
    Next
    INDEX
    Explanations

    methods in a class definition in Java, particularly `public void` methods and methods annotated with `@Override`.

    oai_token-act-pair · gemini-2.0-flash

    public

    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
    fromnode
    -0.52
     Personal
    -0.50
    towa
    -0.49
    ValueGenerated
    -0.48
     Famili
    -0.47
    styleUrls
    -0.47
     StatefulWidget
    -0.47
    IntoConstraints
    -0.47
    DockStyle
    -0.44
    Personal
    -0.44
    POSITIVE LOGITS
     aDecoder
    0.65
     חיצוניים
    0.65
    tvguidetime
    0.62
    évaluateur
    0.61
    UserScript
    0.59
     Administrativna
    0.59
    躇
    0.57
    APORE
    0.56
     kasarigan
    0.55
    醐
    0.54
    Activations Density 0.111%

    No Known Activations