© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14850
    Prev
    Next
    INDEX
    Explanations

    URLs and HTML tags

    oai_token-act-pair · gemini-2.0-flash

    URLs and network-related terms

    np_token-act-pair-logits · gpt-4o-mini

    /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    amaño
    -0.90
    túi
    -0.80
    sữa
    -0.79
    arangay
    -0.77
    Màu
    -0.77
    ousand
    -0.73
    ousands
    -0.73
    twimg
    -0.72
    buntu
    -0.72
    setArguments
    -0.72
    POSITIVE LOGITS
    w
    0.68
    j
    0.65
    h
    0.65
    int
    0.60
    f
    0.60
    x
    0.56
    k
    0.55
    list
    0.55
    ob
    0.54
    new
    0.54
    Activations Density 5.635%

    No Known Activations