© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15749
    Prev
    Next
    INDEX
    Explanations

    sentences that are part of a discussion between people

    oai_token-act-pair · gemini-2.0-flash

    introducing a topic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    )";
    -0.79
    ."</
    -0.79
    UserScript
    -0.79
    >");
    -0.75
    __':
    -0.74
     Wikimedijinoj
    -0.73
     AssemblyCompany
    -0.73
    >\<^
    -0.72
     MediatR
    -0.71
     />';
    -0.71
    POSITIVE LOGITS
    смотрим
    0.57
    いきましょう
    0.56
    .
    0.56
    ########.
    0.54
    CrossRef
    0.54
     détaillé
    0.52
    Step
    0.51
    CodeAttribute
    0.50
     podemos
    0.50
     evident
    0.50
    Activations Density 1.590%

    No Known Activations