© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9267
    Prev
    Next
    INDEX
    Explanations

    terms related to database operations, specifically SQL insertions and queries

    oai_token-act-pair · gemini-2.0-flash

    insert

    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
     insert
    -2.39
    insert
    -2.39
     Insert
    -2.30
    Insert
    -2.22
     inserts
    -1.93
     INSERT
    -1.89
    INSERT
    -1.84
     inserted
    -1.82
     inserting
    -1.80
     insertion
    -1.72
    POSITIVE LOGITS
    ReusableCell
    0.81
    didSet
    0.75
    esModule
    0.69
    ToBounds
    0.69
    存于互联网档案馆
    0.67
    +#+#
    0.61
    MemoryWarning
    0.57
     BoxFit
    0.55
    SwitchCompat
    0.54
    
    0.54
    Activations Density 2.412%

    No Known Activations