© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6771
    Prev
    Next
    INDEX
    Explanations

    code-related terms concerning properties and arrays

    oai_token-act-pair · gemini-2.0-flash

    Property

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Property
    -0.66
    featureID
    -0.65
    ConstraintMaker
    -0.64
     member
    -0.55
    property
    -0.54
    FieldDescriptor
    -0.54
     property
    -0.53
    membre
    -0.52
     Property
    -0.52
    <bos>
    -0.51
    POSITIVE LOGITS
    AndEndTag
    0.81
    expandindo
    0.67
     strdup
    0.61
     jsPsych
    0.59
     Carré
    0.58
    printStackTrace
    0.58
     Sepp
    0.57
    !("{}",
    0.57
    localctx
    0.55
    extAlignment
    0.55
    Activations Density 7.659%

    No Known Activations