© 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. 3041
    Prev
    Next
    INDEX
    Explanations

    parts of code that use common programming structures like loops, if statements, and assignments involving strings

    oai_token-act-pair · gemini-2.0-flash

    range

    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
    <bos>
    -0.69
     individuelles
    -0.68
     individuel
    -0.65
     câte
    -0.64
     وتسجيلات
    -0.61
     Ogni
    -0.60
     individually
    -0.59
    aarrggbb
    -0.58
     Leur
    -0.58
     individuelle
    -0.57
    POSITIVE LOGITS
    RegressionTest
    0.67
    Demografía
    0.66
    orszá
    0.56
    /***/
    0.54
    ULATED
    0.52
    ilim
    0.51
    namon
    0.50
    alot
    0.49
    supervised
    0.48
     <<<<<<<<<<<<<<
    0.48
    Activations Density 5.378%

    No Known Activations