© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10271
    Prev
    Next
    INDEX
    Explanations

    LaTeX math mode code

    oai_token-act-pair · gemini-2.0-flash

    text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    (&:
    -0.66
    ↵↵
    -0.53
    prior
    -0.52
    <h2>
    -0.52
    ticularly
    -0.50
    {{\
    -0.50
     variant
    -0.49
    setVerticalGroup
    -0.49
    ril
    -0.48
     Particularly
    -0.48
    POSITIVE LOGITS
     ProtoMessage
    0.89
    windowFixed
    0.84
     himo
    0.84
     pinulongan
    0.81
     defaultstate
    0.77
    MigrationBuilder
    0.77
    IUrlHelper
    0.75
     noDo
    0.70
     propOrder
    0.70
    featureID
    0.68
    Activations Density 3.137%

    No Known Activations