© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12994
    Prev
    Next
    INDEX
    Explanations

    HTML and XML encoded ampersands that might be part of URLs

    oai_token-act-pair · gemini-2.0-flash

    amp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    EndContext
    -0.86
    mybatisplus
    -0.76
    disambiguation
    -0.73
    erover
    -0.71
    typeorm
    -0.71
    queryInterface
    -0.70
     BrowserModule
    -0.69
     onOptions
    -0.69
    Hauptartikel
    -0.69
    ectoria
    -0.67
    POSITIVE LOGITS
    <bos>
    1.21
    ↵↵
    0.64
    '
    0.61
    ↵
    0.48
    The
    0.46
    [toxicity=0]
    0.45
     dø
    0.44
    <h2>
    0.42
    I
    0.42
    ’
    0.40
    Activations Density 4.379%

    No Known Activations