© 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. 5070
    Prev
    Next
    INDEX
    Explanations

    the name "Hiranyakashipu" and "continue reading" arrows, but also has weak responses to other kinds of maps.

    oai_token-act-pair · gemini-2.0-flash

    anyak

    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
    <bos>
    -1.21
    <h1>
    -0.68
     שוליים
    -0.61
     Waray
    -0.61
     مشين
    -0.61
    stateProvider
    -0.60
     thiệu
    -0.59
    <h2>
    -0.58
    Datuak
    -0.57
    তথ্যসূত্র
    -0.56
    POSITIVE LOGITS
     ComVisible
    0.60
    principalColumn
    0.56
     continuant
    0.54
    acht
    0.52
     Sélectionnez
    0.49
     preferências
    0.48
    autoIncrement
    0.47
     responsabilité
    0.47
    geslacht
    0.47
    biendo
    0.46
    Activations Density 0.759%

    No Known Activations