© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11886
    Prev
    Next
    INDEX
    Explanations

    opencv code and image processing concepts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    
    -0.78
     resourceCulture
    -0.73
    
    -0.64
     Walkover
    -0.63
    AddTagHelper
    -0.63
    Portail
    -0.63
     الرياضيه
    -0.62
    AnchorStyles
    -0.61
    abstractmethod
    -0.60
    MigrationBuilder
    -0.60
    POSITIVE LOGITS
    rects
    0.58
    visualize
    0.58
    centroids
    0.56
     nhan
    0.53
    clustering
    0.52
    camps
    0.51
    contours
    0.51
    igsaw
    0.49
    bounding
    0.49
    invasion
    0.47
    Activations Density 12.441%

    No Known Activations