© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11408
    Prev
    Next
    INDEX
    Explanations

    words related to legal judgments and determinations

    oai_token-act-pair · gemini-2.0-flash

    void and variations

    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
    
    -0.93
    artifactId
    -0.68
     BoxFit
    -0.65
    XmlAccessorType
    -0.64
    fromnode
    -0.60
    帖最后由
    -0.59
     transférez
    -0.59
     FileInputStream
    -0.59
    tvguidetime
    -0.57
    hört
    -0.55
    POSITIVE LOGITS
     cancelled
    0.63
    CANCE
    0.59
     invalid
    0.57
     annul
    0.57
     cancell
    0.57
     cancel
    0.57
     CANCEL
    0.55
     invalidate
    0.54
     canceled
    0.53
     nul
    0.53
    Activations Density 1.460%

    No Known Activations