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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4536
    Prev
    Next
    INDEX
    Explanations

    HTML documents containing URLs and references to web technologies like HTTP, CSS, and Javascript

    oai_token-act-pair · gemini-2.0-flash

    URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    談社
    -0.40
    lossians
    -0.36
    Treating
    -0.36
     Sustain
    -0.36
    åga
    -0.35
     INF
    -0.35
    тона
    -0.35
    Aff
    -0.35
     Towards
    -0.34
     Treating
    -0.34
    POSITIVE LOGITS
    >--}}
    0.78
    aarrggbb
    0.76
    UnsafeEnabled
    0.73
    Rohy
    0.71
    %";
    0.71
    WebVitals
    0.68
    SharedCtor
    0.68
    protoc
    0.68
    ?";
    0.68
    WebServlet
    0.68
    Activations Density 5.857%

    No Known Activations