© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9750
    Prev
    Next
    INDEX
    Explanations

    references to turning and switches

    oai_token-act-pair · 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
    الحياه
    -0.69
    usammen
    -0.68
    رشف
    -0.66
    ,:);
    -0.65
    Portail
    -0.64
    Slf
    -0.64
     فريبيس
    -0.63
     doInBackground
    -0.62
    KommentareTeilen
    -0.61
     >=",
    -0.61
    POSITIVE LOGITS
    digkeit
    0.46
    BoxShadow
    0.46
    ulink
    0.44
     then
    0.44
     TAMBÉM
    0.43
     battu
    0.43
    QMetaType
    0.43
    copal
    0.42
    лег
    0.42
    noin
    0.42
    Activations Density 1.657%

    No Known Activations