© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12140
    Prev
    Next
    INDEX
    Explanations

    words related to the beginning or continuation of a process plus various seemingly unrelated words, including bits of code

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    VersionUID
    -0.61
    Filmografia
    -0.60
    animity
    -0.55
    forChild
    -0.53
    %'
    -0.52
     StatefulWidget
    -0.52
    __':
    -0.51
     traps
    -0.51
     flows
    -0.50
    })));
    -0.50
    POSITIVE LOGITS
     ModelExpression
    0.70
    bootstrapcdn
    0.62
    IMPORTED
    0.62
     resourceCulture
    0.61
     pinulongan
    0.60
    EndContext
    0.57
    efeller
    0.57
    ArrowToggle
    0.56
    tagHelper
    0.55
    клопе
    0.54
    Activations Density 5.319%

    No Known Activations