© 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. 10409
    Prev
    Next
    INDEX
    Explanations

    terms related to magnetic resonance imaging and data reconstruction

    oai_token-act-pair · gemini-2.0-flash

    values

    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
    ArgsConstructor
    -0.87
     MessageBoxIcon
    -0.72
    HtmlAttribute
    -0.71
     ""],
    -0.69
    PyExc
    -0.68
    reportWebVitals
    -0.67
    StoryboardSegue
    -0.67
    帖最后由
    -0.66
    Portály
    -0.65
    ANTLR
    -0.65
    POSITIVE LOGITS
     žen
    0.50
     grano
    0.45
     Infórmanos
    0.44
     admiten
    0.42
     famiglie
    0.40
     anunci
    0.40
    už
    0.40
    <bos>
    0.40
     femei
    0.40
    '
    0.38
    Activations Density 2.901%

    No Known Activations