© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5465
    Prev
    Next
    INDEX
    Explanations

    code snippets and phrases containing "self" or "#"

    oai_token-act-pair · gemini-2.0-flash

    code comments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    //
    -0.75
    ///
    -0.60
    dy
    -0.55
    os
    -0.55
    es
    -0.54
    Die
    -0.52
     tend
    -0.52
     poros
    -0.52
    des
    -0.52
     mati
    -0.52
    POSITIVE LOGITS
    <bos>
    1.33
     feroit
    1.00
     Efq
    0.98
     étoit
    0.96
     auroit
    0.92
     autorytatywna
    0.91
     EClass
    0.90
    berdayakan
    0.90
    XmlAccessorType
    0.90
     engraçadas
    0.89
    Activations Density 0.280%

    No Known Activations