© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9561
    Prev
    Next
    INDEX
    Explanations

    proper nouns with common alphanumeric abbreviations

    oai_token-act-pair · gemini-2.0-flash

    Code/technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    \\
    -0.45
    <eos>
    -0.45
    ↵
    -0.43
     vanskelig
    -0.42
     (
    -0.41
    /
    -0.39
     [
    -0.39
     bakım
    -0.38
    ség
    -0.38
     +
    -0.38
    POSITIVE LOGITS
    SourceChecksum
    1.29
    tagHelperRunner
    1.28
    contentLoaded
    1.24
     beginnetje
    1.13
    fjspx
    1.09
    InjectAttribute
    1.02
    GEBURTSDATUM
    1.00
    DockStyle
    0.98
    titleMargin
    0.96
    MLLoader
    0.95
    Activations Density 4.757%

    No Known Activations