© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12166
    Prev
    Next
    INDEX
    Explanations

    a mix of political terms, European languages, and technical climbing difficulty

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Paglinawan
    -0.71
    DockStyle
    -0.65
    XmlIgnore
    -0.59
    िखित
    -0.57
     clearColor
    -0.51
    czegó
    -0.48
    kmale
    -0.48
    theless
    -0.48
    ChildScrollView
    -0.48
    Bibliografie
    -0.48
    POSITIVE LOGITS
    tagHelperRunner
    0.56
    subpackage
    0.52
     Versch
    0.50
    })));
    0.48
    ತ್ತ
    0.45
    食い
    0.45
     Italijani
    0.44
    IsContent
    0.44
     Pain
    0.43
    odd
    0.43
    Activations Density 0.185%

    No Known Activations