© 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. 10593
    Prev
    Next
    INDEX
    Explanations

    GUI elements and related actions like checking boxes, setting options, or selecting items from a menu.

    oai_token-act-pair · gemini-2.0-flash

    User interfaces/settings

    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
    <bos>
    -0.52
    UMBIA
    -0.52
    vertx
    -0.51
     UITableView
    -0.49
     qualified
    -0.47
    AddHtmlAttribute
    -0.47
     Kur
    -0.46
    italien
    -0.44
    SBATCH
    -0.43
    qualified
    -0.42
    POSITIVE LOGITS
    InitVars
    0.74
     skydd
    0.73
     تضيفلها
    0.69
    getMenuInflater
    0.67
     škoda
    0.65
    FormTagHelper
    0.64
     vägen
    0.64
     förslag
    0.63
    PerformLayout
    0.63
    IsPostBack
    0.63
    Activations Density 0.733%

    No Known Activations