© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1100
    Prev
    Next
    INDEX
    Explanations

    code-related keywords such as "set", "get", "flags", "selector", and "optional"

    oai_token-act-pair · gemini-2.0-flash

    set

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    set
    -1.79
    Set
    -1.70
     set
    -1.67
     Set
    -1.66
    SET
    -1.42
     SET
    -1.41
     Sets
    -1.19
    Sets
    -1.16
     sets
    -1.16
    sets
    -1.13
    POSITIVE LOGITS
    tagHelperRunner
    0.85
    EndProject
    0.68
    AutoScaleMode
    0.66
     שוליים
    0.63
     مشين
    0.63
    ChildScrollView
    0.56
     NSCoder
    0.56
     MainAxisSize
    0.55
    simpleType
    0.53
     InputDecoration
    0.52
    Activations Density 4.108%

    No Known Activations