© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4371
    Prev
    Next
    INDEX
    Explanations

    LaTeX blocks using the `aligned` environment

    oai_token-act-pair · gemini-2.0-flash

    aligned

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     createSlice
    -0.69
    setVerticalGroup
    -0.68
     BrowserModule
    -0.66
    esModule
    -0.65
     InputDecoration
    -0.65
    :✨
    -0.64
     виправивши
    -0.63
     [*]
    -0.62
     NSCoder
    -0.62
     viewDidLoad
    -0.60
    POSITIVE LOGITS
    <bos>
    2.48
    '
    0.71
    ’
    0.62
     the
    0.59
     and
    0.53
    #
    0.53
     to
    0.50
    ↵↵
    0.49
     that
    0.47
    -
    0.43
    Activations Density 0.106%

    No Known Activations